Triple
T3603073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terriers |
E76302
|
entity |
| Predicate | competesInSport |
P39898
|
FINISHED |
| Object | ice hockey |
—
|
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: ice hockey | Statement: [Terriers, competesInSport, ice hockey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: competesInSport Context triple: [Terriers, competesInSport, ice hockey]
-
A.
sportsInvolvement
Indicates the nature or extent of an entity’s participation in, association with, or role within a sport or sporting activity.
-
B.
includesSport
Indicates that one entity contains, offers, or features a particular sport as part of its activities, content, or composition.
-
C.
competeIn
chosen
Indicates that an entity takes part as a contender in a particular event, activity, or domain where performance is compared against others.
-
D.
representsInSport
Indicates that one entity serves as an official representative of another entity within the context of a particular sport or sporting domain.
-
E.
competitionOf
Indicates a relationship where one entity is the competitive event, contest, or rivalry involving another entity.
- 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_69ad85d93dcc819094fba90cf70f4996 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc1df08a48190a4a4a20c8821b321 |
completed | March 8, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69adb83b66708190bb9d2f23d6fd308e |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:22 p.m.