Triple
T4489217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phil Esposito |
E107325
|
entity |
| Predicate | scoringRecordHeld |
P2722
|
FINISHED |
| Object | single-season NHL goals record (historical) |
—
|
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: single-season NHL goals record (historical) | Statement: [Phil Esposito, scoringRecordHeld, single-season NHL goals record (historical)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scoringRecordHeld Context triple: [Phil Esposito, scoringRecordHeld, single-season NHL goals record (historical)]
-
A.
recordHeld
chosen
Indicates that one entity possesses or maintains a particular record associated with another entity or context.
-
B.
recordHeldIn
Indicates that a record is stored, maintained, or kept within a particular location, system, or repository.
-
C.
recordHighScoringForWinner
Indicates that a record is kept of the highest score achieved by the winning entity in a given context or event.
-
D.
recordHeldFrom
Indicates that a record or position was held by an entity starting from a specified point in time.
-
E.
scoredFor
Indicates that one entity achieved points or a score on behalf of another entity, such as a player scoring for a team.
- 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_69bd43f84f788190a1383579c4a595be |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd556d29f08190bab1e872dd7e819f |
completed | March 20, 2026, 2:10 p.m. |
| PD | Predicate disambiguation | batch_69bd5213e3d0819094b026989e686f01 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 12:59 p.m.