Triple
T1400947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Connie Mack Stadium |
E30779
|
entity |
| Predicate | finalMLBGame |
P18317
|
FINISHED |
| Object | 1970 |
—
|
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: 1970 | Statement: [Connie Mack Stadium, finalMLBGame, 1970]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalMLBGame Context triple: [Connie Mack Stadium, finalMLBGame, 1970]
-
A.
finalMLBSeason
Indicates the specific MLB season that was the last one in which the subject participated or was active.
-
B.
finalMlbGameDate
chosen
Indicates the calendar date on which an entity’s final Major League Baseball game took place.
-
C.
finalMLBTeam
Indicates the Major League Baseball team with which an entity was last or ultimately associated, such as the final team they played for or were on the roster of.
-
D.
finalHomeGameResult
Indicates the outcome of an entity’s last home game in a given context or season.
-
E.
allGamesCompleteGameShutouts
Indicates that every game in the relevant set was a complete game in which the opposing team was held scoreless (a shutout).
- 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_69a498fd4e408190bd73eca30ea9754c |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c39da20c8190b9c82cc4ad747c66 |
completed | March 1, 2026, 10:54 p.m. |
| PD | Predicate disambiguation | batch_69a4bf017f8081908572121560ec621f |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.