Triple
T1361272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NCAA Men's Ice Hockey Championship |
E29102
|
entity |
| Predicate | frozenFourParticipants |
P27447
|
FINISHED |
| Object | 4 teams |
—
|
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: 4 teams | Statement: [NCAA Men's Ice Hockey Championship, frozenFourParticipants, 4 teams]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frozenFourParticipants Context triple: [NCAA Men's Ice Hockey Championship, frozenFourParticipants, 4 teams]
-
A.
frozenIn
Indicates that one entity is immobilized or preserved in a solid, frozen state within or by another entity.
-
B.
frozenFrom
Indicates that one entity has been preserved or immobilized by being frozen starting from another entity, source, or prior state.
-
C.
fourthPlace
Indicates that an entity holds the fourth position or rank in an ordered sequence, competition, or hierarchy.
-
D.
opposingParticipants
Indicates that the related entities are participants positioned in opposition to each other within the same interaction, event, or context.
-
E.
finalFourAppearance
Indicates that an entity has reached the semifinal round (Final Four) of a tournament or championship.
- 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_69a498d77abc8190913bf57e5f51d2c4 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c2b2fb448190bef31375169b4666 |
completed | March 1, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69a4bef945c08190a027472fdd695ea5 |
completed | March 1, 2026, 10:34 p.m. |
| PDg | Predicate description generation | batch_69a4c06721488190ac7f6e012f21af3d |
completed | March 1, 2026, 10:40 p.m. |
Created at: March 1, 2026, 7:57 p.m.