Triple
T2195034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | bloody sock game |
E49951
|
entity |
| Predicate | positionPlayedByCurtSchilling |
P36698
|
FINISHED |
| Object | starting pitcher |
—
|
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: starting pitcher | Statement: [bloody sock game, positionPlayedByCurtSchilling, starting pitcher]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionPlayedByCurtSchilling Context triple: [bloody sock game, positionPlayedByCurtSchilling, starting pitcher]
-
A.
startingPitcherForAwayTeam
Indicates that one entity is the pitcher who starts the game on the mound for the visiting (away) baseball team in a particular game.
-
B.
convertedToPitcher
Indicates that an entity changed roles or status to become a pitcher.
-
C.
careerInningsPitched
Indicates the total number of innings a player has pitched over the course of their entire career.
-
D.
noHitterOpponent
Indicates that the specified opponent team or player was the team/player against whom a no-hitter was pitched.
-
E.
RedSoxStartingPitcher
Indicates that the subject is serving as the starting pitcher for the Boston Red Sox in a given game.
- 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_69a88aaba3c48190b351cab9b26989ff |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abbf764e348190896af2aeb5520038 |
completed | March 7, 2026, 6:02 a.m. |
| PD | Predicate disambiguation | batch_69abbda52328819089c7ab111bebb0ca |
completed | March 7, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69abbea8bd4881908f72019a5acf6174 |
completed | March 7, 2026, 5:59 a.m. |
Created at: March 4, 2026, 7:46 p.m.