Triple
T5355036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georges Vezina |
E102668
|
entity |
| Predicate | gamesPlayedConsecutively |
P14549
|
FINISHED |
| Object | 328 regular-season games |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 328 regular-season games | Statement: [Georges Vezina, gamesPlayedConsecutively, 328 regular-season games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gamesPlayedConsecutively Context triple: [Georges Vezina, gamesPlayedConsecutively, 328 regular-season games]
-
A.
consecutiveGamesPlayed
chosen
Indicates that an entity has participated in a series of games without interruption, one immediately following another.
-
B.
gamesPlayed
Indicates the number or set of games that an entity has participated in or completed.
-
C.
isConsecutiveTitleGameAppearance
Indicates that an entity’s appearance in a title game occurs in back-to-back seasons or events without interruption.
-
D.
mostConsecutiveWinsCount
Indicates the highest number of wins achieved in a row within a given sequence or context.
-
E.
consecutiveGamesRecordHeldFrom
Indicates that one entity held the record for most consecutive games played starting from a specified point in time.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69bd43d8f7248190b64c140734b5c9a8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd862dbb008190aef653acddafd38b |
completed | March 20, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69bd845c6f108190832a8d14b356368a |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:01 p.m.