Triple
T37001930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2015 Major League Baseball postseason |
E915374
|
entity |
| Predicate | NLCSParticipant |
P180812
|
FINISHED |
| Object | New York Mets |
—
|
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: New York Mets | Statement: [2015 Major League Baseball postseason, NLCSParticipant, New York Mets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: NLCSParticipant Context triple: [2015 Major League Baseball postseason, NLCSParticipant, New York Mets]
-
A.
participantFrom
Indicates that a participant originates from, is associated with, or comes out of a specified source, group, or context.
-
B.
participantWith
chosen
Indicates that an entity takes part in an event, activity, or process together with another specified entity.
-
C.
allegedParticipant
Indicates that an entity is claimed or suspected to have taken part in an event, action, or situation, without this participation being confirmed as fact.
-
D.
collaboratingParty
Indicates that an entity is actively working together with another entity toward a shared goal, project, or activity.
-
E.
notableParticipant
Indicates that an entity plays a significant or distinguished role as a participant in an event, activity, or context.
- 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_69f76e8f1a8c81909db172ed31304971 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb154c0fe08190a2e41e7a29b6055f |
completed | May 6, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f9fecc005c8190be082a8689193745 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:14 p.m.