You asked
When does the game end?
Answered counted as answeredAsked with: El Grandebg-93-en-1e
The game ends after the 3rd general scoring [1]. After this 3rd scoring, you proceed with "End of the game" [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 706 ms · ask 6535 ms · total 7280 ms
- single-flight (PR-5)
- queued 0 ms · generation 7280 ms
- retrieval refs (raw)
- [{"page": 8, "score": 0.04918, "snippet": "The game ends after the 3rd general scoring. The player with the most points wins the game and is dubbed El Grande . In case of a tie, you share the victory (or another place). Example: You move the Scoring tile to Castilla to reduce the majority points for this region. The regions are scored in the", "headingPath": "End of the game", "sharpsignalDocId": 162}, {"page": 4, "score": 0.048387, "snippet": "You try to gain majority in the regions of Spain by cleverly placing your Caballeros. During each scoring, you'll earn points depending on your majorities. The player with the most points at the end of the game wins. The game plays over 9 rounds. First, you play Power cards to determine turn order. ", "headingPath": "Goal of the Game · Gameplay · 1. Reveal Action cards · 2. Play Power cards · 3. Take a turn", "sharpsignalDocId": 162}, {"page": 8, "score": 0.046176, "snippet": "Score each region in the order shown on the Scoring overview, from top to bottom. Scoring regions follows the same rules as scoring the Castillo. First you determine how many Caballeros each player has in the region. Then, players with the 1st, 2nd, and 3rd most Caballeros get points according to th", "headingPath": "c) Score each region · Resolving ties · King's bonus and Grande's bonus · Scoring tile", "sharpsignalDocId": 162}, {"page": 7, "score": 0.046175, "snippet": "Whoever played the lowest Power card in this round takes the First Player marker . Put your played Power card face down on your discard pile. Move the Round marker 1 space down . If the marker lands on a spot with the next digit, a new round begins as just described. If the Round marker lands on a s", "headingPath": "4. End of the round · 5. General scoring · a) Set your Secret disc · b) Score the Castio and move Cabaeros to a region", "sharpsignalDocId": 162}, {"page": 6, "score": 0.045475, "snippet": "Each Action card shows a Special action that you may perform. You may also choose to not perform the Special action at all and only place your Caballeros (p. 5). If you perform the Special action, you must perform as much of the action as possible , even if it benefits another player more than you (", "headingPath": "Special action · The Castio · Attention: The King's region is taboo! · 4. End of the round", "sharpsignalDocId": 162}, {"page": 12, "score": 0.045002, "snippet": "Only with this card, you can throw Grandes into the Castillo . When scoring the Castillo, you can get the Grande's bonus. Then move your Grande using the Secret disc (along with your Caballeros). Special case: After scoring the Castillo with the 'Revelation' card, throw the Grandes back into the Cas", "headingPath": "Competition · Chalet · Rebeion · Infiltration · Stand-in · Veto", "sharpsignalDocId": 162}, {"page": 9, "score": 0.031746, "snippet": "You can also play a shorter game that lasts only 6 rounds. During setup, start the Round marker on space 2. When advancing the Round marker, skip spaces 4 and 7. Set up the game as described on p. 2 and 3 with the following changes: Flip the game board. The 2- and 3-player side should now be visible", "headingPath": "Short game · 2-player game", "sharpsignalDocId": 162}, {"page": 9, "score": 0.030118, "snippet": "At the beginning of each round, draw 2 Region cards. Place 2 Caballeros of the dummy in each of the drawn regions. If all 30 are on the game board, do not draw any more Region cards. If a card shows the King's region, do not place any Caballeros there. Then place the cards on a discard pile. After e", "headingPath": "Gameplay changes: · 3-player game · Mini expansion: 'New Regency'", "sharpsignalDocId": 162}]
- citations (raw)
- [{"page": 8, "quote": null, "headingPath": "End of the game", "sharpsignalDocId": 162}, {"page": 8, "quote": null, "headingPath": "c) Score each region · Resolving ties · King's bonus and Grande's bonus · Scoring tile", "sharpsignalDocId": 162}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 162 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 162 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 5, 2026 13:59
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 El Grande — Rulebook (corpus doc 162) | End of the game | p.8 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK El Grande — Rulebook (corpus doc 162) | Goal of the Game · Gameplay · 1. Reveal Action cards · 2. Play Power cards · 3. Take a turn | p.4 | 0.048387 (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 El Grande — Rulebook (corpus doc 162) | c) Score each region · Resolving ties · King's bonus and Grande's bonus · Scoring tile | p.8 | 0.046176 (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 El Grande — Rulebook (corpus doc 162) | 4. End of the round · 5. General scoring · a) Set your Secret disc · b) Score the Castio and move Cabaeros to a region | p.7 | 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 |
| #5 | RULEBOOK El Grande — Rulebook (corpus doc 162) | Special action · The Castio · Attention: The King's region is taboo! · 4. End of the round | p.6 | 0.045475 (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 El Grande — Rulebook (corpus doc 162) | Competition · Chalet · Rebeion · Infiltration · Stand-in · Veto | p.12 | 0.045002 (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 El Grande — Rulebook (corpus doc 162) | Short game · 2-player game | p.9 | 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 |
| #8 | RULEBOOK El Grande — Rulebook (corpus doc 162) | Gameplay changes: · 3-player game · Mini expansion: 'New Regency' | p.9 | 0.030118 (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 El Grande — Rulebook (corpus doc 162) | End of the game | p.8 | no quote on the wire |
| [2] | RULEBOOK El Grande — Rulebook (corpus doc 162) | c) Score each region · Resolving ties · King's bonus and Grande's bonus · Scoring tile | p.8 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 706 ms · first delta 6945 ms · total 7280 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 706 ms · ask 6535 ms · gateway work 7280 ms · total 7280 ms
- tokens in (the prompt the answerer read)
- 4057
- tokens out (what the answerer generated)
- 33
- tok/sec
- 138.1 tok/sec — 33 output tokens in 0.239 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 19s 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
- NOT_SETUP_SHAPED — no setup-shape pattern matched this question
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 84), 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.