Triple
T1112172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2008 NBA Finals |
E11018
|
entity |
| Predicate | largestComebackInGame4 |
P7472
|
FINISHED |
| Object | 24 points |
—
|
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: 24 points | Statement: [2008 NBA Finals, largestComebackInGame4, 24 points]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: largestComebackInGame4 Context triple: [2008 NBA Finals, largestComebackInGame4, 24 points]
-
A.
teamInComeback
Indicates that a team participates in or is responsible for a comeback, overturning a losing or disadvantaged position.
-
B.
decidingGameComebackWin
Indicates that a team or player secured a win in the final, decisive game of a series by overcoming a deficit and mounting a comeback.
-
C.
opponentInComeback
Indicates that an entity serves as the opposing side or competitor in a situation characterized as a comeback (e.g., recovering from a disadvantage).
-
D.
homeTeamForGames3And4
Indicates which team serves as the home team in both games 3 and 4 of a series or schedule.
-
E.
notablePlayoffStatistic
chosen
Indicates that there exists a significant or distinguished statistical achievement associated with an entity’s performance in playoff competition.
- 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_69a493252a648190ac48f8742474a5e8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4bbd92a8c8190a16e55f3f739010f |
completed | March 1, 2026, 10:21 p.m. |
| PD | Predicate disambiguation | batch_69a4bb42990c819080db96478fd4977e |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:43 p.m.