Triple
T3507001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1977 NBA Finals |
E74099
|
entity |
| Predicate | seriesOutcomeAfterTwoGames |
P10847
|
FINISHED |
| Object | Philadelphia 76ers led 2–0 |
—
|
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: Philadelphia 76ers led 2–0 | Statement: [1977 NBA Finals, seriesOutcomeAfterTwoGames, Philadelphia 76ers led 2–0]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seriesOutcomeAfterTwoGames Context triple: [1977 NBA Finals, seriesOutcomeAfterTwoGames, Philadelphia 76ers led 2–0]
-
A.
finalHomeGameResult
Indicates the outcome of an entity’s last home game in a given context or season.
-
B.
gameOutcome
Indicates the result or final status of a game, such as which side won, lost, or if it ended in a draw.
-
C.
subsequentOutcomeForWinner
Indicates that the predicate links a winner to an outcome or event that occurs to or for them after their initial victory.
-
D.
seriesWinningGame
Indicates that a particular game is the decisive or clinching game in which one side wins the overall series.
-
E.
seriesScoreAfterGame
chosen
Indicates the updated score or standing of a multi-game series immediately following the completion of a specific game.
- 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_69ad85ce7a9c81909ddc5cf0cb67a6e3 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbbf52bd8819085a2ac5f48cc5c68 |
completed | March 8, 2026, 6:12 p.m. |
| PD | Predicate disambiguation | batch_69adae0e770481908528fa35eda53003 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:18 p.m.