Triple
T36783056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1997 NBA Finals |
E908824
|
entity |
| Predicate | game5StarPerformance |
P186292
|
FINISHED |
| Object | Michael Jordan |
—
|
NE NERFINISHED |
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: Michael Jordan | Statement: [1997 NBA Finals, game5StarPerformance, Michael Jordan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: game5StarPerformance Context triple: [1997 NBA Finals, game5StarPerformance, Michael Jordan]
-
A.
game5Description
Indicates the textual description or summary associated with the fifth game in a sequence or collection of games.
-
B.
starsPlay
Indicates that an entity has a leading or prominent acting role in a performance, production, or event.
-
C.
gameplayImpact
Indicates how one element in a game affects the mechanics, difficulty, or overall experience of playing that game.
-
D.
launchPerformance
Indicates the performance characteristics or outcomes associated with initiating or starting an action, process, or product.
-
E.
seriesScore
Indicates the numerical outcome or standing of participants within a multi-part series, such as games, matches, or episodes, relative to one another.
- F. None of above. chosen
Provenance (4 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_69f76e7a937c81909ed7359641e670f6 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7cabacc1481909e839454ce1057f7 |
completed | May 3, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
| PDg | Predicate description generation | batch_69f7c9f4c7c48190ba918d8d5dc8dfd9 |
completed | May 3, 2026, 10:19 p.m. |
Created at: May 3, 2026, 4:12 p.m.