Triple
T35497775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Stewart |
E1025914
|
entity |
| Predicate | refereedInLeague |
P74125
|
FINISHED |
| Object | National Hockey League |
—
|
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: National Hockey League | Statement: [Paul Stewart, refereedInLeague, National Hockey League]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refereedInLeague Context triple: [Paul Stewart, refereedInLeague, National Hockey League]
-
A.
refereedLeague
Indicates that an entity served as a referee or officiated in a particular sports league.
-
B.
refereedMatch
Indicates that an entity served as the referee or official overseeing and enforcing the rules in a particular match or game.
-
C.
refereedCompetition
Indicates that a competition is overseen by an official referee or judging authority who enforces rules and makes binding decisions.
-
D.
refersToLeague
Indicates that one entity is associated with, mentions, or designates a particular sports or competitive league as its related organization.
-
E.
officiatedInLeague
chosen
Indicates that an official (such as a referee or umpire) performed their officiating duties within a particular sports league.
- 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_69f76dfc9c60819089c4217d93922615 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fe779248c081909f0ed1a2a0df23db |
completed | May 8, 2026, 11:53 p.m. |
| PD | Predicate disambiguation | batch_69fe76eaf6d48190998bc7168749cc42 |
completed | May 8, 2026, 11:51 p.m. |
Created at: May 3, 2026, 4:04 p.m.