You asked
How do I setup the game?
Answered counted as answeredAsked with: A Game of Thrones: The Board Game (Second Edition)bg-103343-en-1e
1. Unfold the game board and place it in the center of the play area [1]. 2. Shuffle the Wildling cards to form a deck and place this deck on the space provided at the top of the game board [1]. 3. Place the Wildling Threat token on the '2' position of the Wildlings track [1]. 4. Separate the Westeros cards into decks according to their roman numeral (I, II, or III), shuffle each deck, and place them separately facedown next to the game board [1]. 5. Collect the Neutral Force tokens marked with the correct range of players and place those tokens on the areas of the game board matching the name on each token, ensuring they are placed face up [1][2]. (Note: In a five-player game, place nine tokens marked '4-6' and '4-5'; in a four-player game, place twelve tokens marked '4-6', '4-5', and '4'; in a three-player game, place fourteen tokens marked '3') [2]. 6. Return any unused Neutral Force tokens to the box [1]. 7. If playing with the Tides of Battle module, shuffle the Tides of Battle cards into a single deck and place it near the game board [3]. 8. Place the Game Round marker on the '1' position of the Round track [4]. 9. Each player selects which House they wish to control (Stark, Lannister, Greyjoy, Tyrell, Baratheon, or Martell), noting that certain Houses are ineligible depending on the number of players [4]. 10. Each player gathers all materials belonging to their House: 1 player screen, 7 House cards, 15 Order tokens, 1 Supply token, 3 Influence tokens, 1 Victory Point token, 1 Garrison token, and all plastic units of their color [4]. 11. Each player takes the player screen representing their House [5]. 12. Each player places their Victory, Supply, and Influence tokens on the game board tracks as instructed by their player screen (sliding Influence tokens to the left in games with fewer than six players) [4]. 13. The Houses occupying the '1' position on each Influence track claim the corresponding Dominance token (the Iron Throne, the Valyrian Steel Blade, or the Messenger Raven token) [4]. 14. If playing a four-player game, place the King's Court Overlay on top of the King's Court Influence track, covering the first four positions [2]. 15. If playing a three-player game, place the King's Court Overlay on top of the King's Court Influence track, covering the first four positions [2]. 16. Each player places all of their starting units on the game board according to the instructions on their player screen [6][4]. 17. Each player places their Garrison token on his home area (matching the area name on the token) [6][4]. 18. Place all Power tokens for all Houses in a central pile known as the 'Power Pool' [6][4]. 19. Each player takes five Power tokens matching his House from the Power Pool [6].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 1072 ms · ask 17422 ms · total 18511 ms
- single-flight (PR-5)
- queued 0 ms · generation 18511 ms
- retrieval refs (raw)
- [{"page": 4, "score": 0.04918, "snippet": "Before playing the game, perform the following steps in order: P G B: Unfold the game board and place it in the center of the play area. P W D W T T: Shuffle the Wildling cards to form a deck. Place this deck on the space provided at the top o", "headingPath": "GAme seTUp", "sharpsignalDocId": 373}, {"page": 28, "score": 0.047371, "snippet": "A G A m e o f T h r o n e s In a five-player game, House Martell cannot be chosen as a player House. During setup for a five-player game, place the nine Neutral Force tokens marked with the '4-6' and '4-5' player ranges on the game board, matching the name on each Neutral Force token to its correspo", "headingPath": "hidden informATion · Five-Player Games · Four-Player Games · Three-Player Games · T-P G S", "sharpsignalDocId": 373}, {"page": 4, "score": 0.046175, "snippet": "Each House is provided a limited number of units, tokens, and cards. If a player is using all his components of a particular type, he may not bring additional components of that type into play. Units that are destroyed in combat (or removed from the board for any other reason) are available to be mu", "headingPath": "E C P", "sharpsignalDocId": 373}, {"page": 4, "score": 0.032258, "snippet": "P U: Each player then places all of his starting units on the game board according to the instructions on his player screen. P G T : Each player places his Garrison token on his home area (matching the area name on the token). G P T: Place all Power tokens (for ", "headingPath": "E C P", "sharpsignalDocId": 373}, {"page": 12, "score": 0.030769, "snippet": "During this phase, players secretly issue orders to areas on the game board. /The Planning Phase consists of the following steps: A O R O U M R During this step, each player must place exactly one Order token facedown (i.e., secretly, his house insignia facing up) o", "headingPath": "The pLAnninG phAse · 1. Assign Orders", "sharpsignalDocId": 373}, {"page": 27, "score": 0.030303, "snippet": "Each player is provided with a player screen to keep certain elements of the game hidden from the other players. From the very beginning of the game, players should always keep their unused Order tokens behind their player screens. Except just prior to any bidding, each player's available power toke", "headingPath": "hidden informATion", "sharpsignalDocId": 373}, {"page": 16, "score": 0.029851, "snippet": "A Game of /Thrones: /The Board Game ends in one of two ways: /end3 /The game reaches the end of the 10th game round. /end3 Immediately after a player controls his seventh area containing a Castle or Stronghold. Each player must, at all times, record the number of areas he controls containing a Castl", "headingPath": "winninG The GAme · C P O E", "sharpsignalDocId": 373}, {"page": 6, "score": 0.02967, "snippet": "Each player takes the player screen that represents his House. /The player screen provides reference information, setup information, and enables players to sort and store components (such as Order tokens) privately during the game. Order token reference Starting units information Starting position o", "headingPath": "T P S · T H W · H L 'Hear Me Roar'", "sharpsignalDocId": 373}]
- citations (raw)
- [{"page": 4, "quote": null, "headingPath": "GAme seTUp", "sharpsignalDocId": 373}, {"page": 28, "quote": null, "headingPath": "hidden informATion · Five-Player Games · Four-Player Games · Three-Player Games · T-P G S", "sharpsignalDocId": 373}, {"page": 29, "quote": null, "headingPath": "Tides of bATTLe", "sharpsignalDocId": 373}, {"page": 4, "quote": null, "headingPath": "E C P", "sharpsignalDocId": 373}, {"page": 6, "quote": null, "headingPath": "T P S · T H W · H L 'Hear Me Roar'", "sharpsignalDocId": 373}, {"page": 4, "quote": null, "headingPath": "E C P", "sharpsignalDocId": 373}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 373 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 373 boosted
- answered-before recall
-
this ruling was answered, so past rulings were not offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- debug row retained until
- Nov 6, 2026 21:10
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the THREE-ARM fuse (full-text + vector + the doc-priority boost arm, which carried the base rulebook and/or the errata corrections this query matched), whose arithmetic ceiling is 0.04918 — all three arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). The measured healthy band 0.016–0.033 was measured on TWO-arm asks and does not bound this one: its high end is the two-arm ceiling, and a third arm has room above it. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.
per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| fused rank | document | heading | page | fused RRF score | snippet chars |
|---|---|---|---|---|---|
| #1 | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | GAme seTUp | p.4 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | hidden informATion · Five-Player Games · Four-Player Games · Three-Player Games · T-P G S | p.28 | 0.047371 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #3 | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | E C P | p.4 | 0.046175 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #4 | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | E C P | p.4 | 0.032258 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #5 | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | The pLAnninG phAse · 1. Assign Orders | p.12 | 0.030769 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #6 | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | hidden informATion | p.27 | 0.030303 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #7 | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | winninG The GAme · C P O E | p.16 | 0.029851 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #8 | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | T P S · T H W · H L 'Hear Me Roar' | p.6 | 0.02967 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
chosen chunks — what the answer actually cited
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | GAme seTUp | p.4 | no quote on the wire |
| [2] | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | hidden informATion · Five-Player Games · Four-Player Games · Three-Player Games · T-P G S | p.28 | no quote on the wire |
| [3] | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | Tides of bATTLe | p.29 | no quote on the wire |
| [4] | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | E C P | p.4 | no quote on the wire |
| [5] | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | T P S · T H W · H L 'Hear Me Roar' | p.6 | no quote on the wire |
| [6] | RULEBOOK A Game of Thrones: The Board Game (Second Edition) — Rulebook (corpus doc 373) | E C P | p.4 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 1072 ms · first delta 14022 ms · total 18511 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 1072 ms · ask 17422 ms · gateway work 18511 ms · total 18511 ms
- tokens in (the prompt the answerer read)
- 4500
- tokens out (what the answerer generated)
- 692
- tok/sec
- 136.2 tok/sec — 692 output tokens in 5.082 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 34s ago)
- stream path
- streamed — the gateway pushed at least one accumulated draft
- watchdog
- first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
- num_ctx · think posture
- both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.
disposition
- outcome
- ANSWERED — Answered
- abstain rationale (n/a — this ruling answered)
- answered — no abstain rationale applies
setup-shape — why the checklist band did or didn't render
- decision
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 301), so "no registered errata card matched" above could never have matched one
Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.