You asked
What does each player take, and what goes in the middle, before we begin?
Answered counted as answeredAsked with: Ankh: Gods of Egyptbg-285967-en-1e
Each player takes the following components belonging to their chosen god: * 1 God figure [1] * 6 Warrior figures [1] * God dashboard [1] * Merged God dashboard [1] * Ankh tokens [1] * Set of 7 Battle cards [1] * Player Aid card [1] * 3 Sun tokens (if the player has Ra) [1] * 3 Underworld tokens (if the player has Osiris) [1] * The Amun token (if the player has Amun) [1] * 1 Follower token [1] Before the game begins, the following are placed in the middle/on the board: * 4 Action markers on the Action tracks of the central dashboard in starting spaces matching the number of players [2] * The Event marker on the first space of the Events track [2] * Monuments (Pyramids, Temples, and Obelisks), Conflict Order tokens, and Camels (as shown in the scenario setup diagram) [2] * Guardian cards (one Level 1, one Level 2, and one Level 3) and a number of their Guardian figures next to the cards based on player count [2]
🔧 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 280 ms · ask 11873 ms · total 12163 ms
- single-flight (PR-5)
- queued 0 ms · generation 12163 ms
- retrieval refs (raw)
- [{"page": 9, "score": 0.032787, "snippet": "During the game, players take turns performing actions including moving their figures on the board to seize control of key territory, summoning Warriors and Guardians to battle their opponents, gaining new Followers, and unlocking new Ankh powers. The 4 possible actions are depicted on the top half ", "headingPath": "CENTRAL DASHBOARD", "sharpsignalDocId": 358}, {"page": 13, "score": 0.032258, "snippet": "Randomly determine a first player (or assign it to the player who owns the most cats). Other players will follow in clockwise seating order around the table. 4 In reverse player order, starting with the last player, each player places their plastic Ankh token on the bottom space of the Devotion trac", "headingPath": "BATTLE CARDS", "sharpsignalDocId": 358}, {"page": 12, "score": 0.031746, "snippet": "Each player chooses one of the mighty gods of Egypt from among those available and takes the following components belonging to that god: 1 God figure 6 Warrior figures God dashboard Merged God dashboard Ankh tokens Set of 7 Battle cards Player Aid card If a player has Ra, they take the 3 Sun tokens.", "headingPath": "BATTLE CARDS", "sharpsignalDocId": 358}, {"page": 32, "score": 0.03125, "snippet": "The player who triggered the event takes the Battle Tiebreaker token. Then, check each region in order: Domination (One Player): Gain 1 Devotion for each Monument majority you have. Then, gain 1 Devotion for dominating the region. Battle (Multiple Players): Disregard players, figures, and Monuments ", "headingPath": "Conflict:", "sharpsignalDocId": 358}, {"page": 25, "score": 0.030769, "snippet": "Only in a game with 3 or more players , at the end of the 3 rd Conflict, the 2 gods with the least Devotion (the ones in the bottom 2 positions in the Devotion track) are at risk of being forgotten by the people of Egypt. To avoid that fate, those 2 gods merge into a single divine entity. The player", "headingPath": "MERGING GODS", "sharpsignalDocId": 358}, {"page": 26, "score": 0.030303, "snippet": "The Ra player destroys all of their Monuments and removes from the game all of their Battle cards, Ankh tokens, and figures, except for their Guardian, which receives an Amun color base. All of Ra ’s Followers are put together with Amun’s pool. The Ra player adjusts their Ankh powers to match those ", "headingPath": "", "sharpsignalDocId": 358}, {"page": 11, "score": 0.029851, "snippet": "Devotion is the measure of how much a god is worshipped by the people of Egypt. Each god's current Devotion level is marked with an Ankh token on the Devotion dashboard. Each god begins the game at the bottom of the Devotion track (the lowest red space), and as they earn more Devotion, their Ankh to", "headingPath": "DEVOTION · BATTLE CARDS", "sharpsignalDocId": 358}, {"page": 13, "score": 0.029412, "snippet": "Follow any Additional Setup Rules as dictated in the scenario book. 12 You are ready to play! There are 3 ways to become the only God of Egypt and win the game: A player wins immediately when their Ankh token reaches the top space of the Devotion track. A player wins immediately if they are the only", "headingPath": "BATTLE CARDS", "sharpsignalDocId": 358}]
- citations (raw)
- [{"page": 12, "quote": null, "headingPath": "BATTLE CARDS", "sharpsignalDocId": 358}, {"page": 13, "quote": null, "headingPath": "BATTLE CARDS", "sharpsignalDocId": 358}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 358 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 358 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 18:22
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 Ankh: Gods of Egypt — Rulebook (corpus doc 358) | CENTRAL DASHBOARD | p.9 | 0.032787 (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 |
| #2 | RULEBOOK Ankh: Gods of Egypt — Rulebook (corpus doc 358) | BATTLE CARDS | p.13 | 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 |
| #3 | RULEBOOK Ankh: Gods of Egypt — Rulebook (corpus doc 358) | BATTLE CARDS | p.12 | 0.031746 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358) | Conflict: | p.32 | 0.03125 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358) | MERGING GODS | p.25 | 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 Ankh: Gods of Egypt — Rulebook (corpus doc 358) | p.26 | 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 Ankh: Gods of Egypt — Rulebook (corpus doc 358) | DEVOTION · BATTLE CARDS | p.11 | 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 Ankh: Gods of Egypt — Rulebook (corpus doc 358) | BATTLE CARDS | p.13 | 0.029412 (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 Ankh: Gods of Egypt — Rulebook (corpus doc 358) | BATTLE CARDS | p.12 | no quote on the wire |
| [2] | RULEBOOK Ankh: Gods of Egypt — Rulebook (corpus doc 358) | BATTLE CARDS | p.13 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 280 ms · first delta 10119 ms · total 12163 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 280 ms · ask 11873 ms · gateway work 12163 ms · total 12163 ms
- tokens in (the prompt the answerer read)
- 4211
- tokens out (what the answerer generated)
- 276
- tok/sec
- 138.3 tok/sec — 276 output tokens in 1.996 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 58s 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
- BEGIN — "begin" / "beginning"
- matched words (in the normalized question)
-
begin
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 287), 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.