Triple
T435572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl XLII |
E10003
|
entity |
| Predicate | refereeRole |
P10316
|
FINISHED |
| Object | head referee |
—
|
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: head referee | Statement: [Super Bowl XLII, refereeRole, head referee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refereeRole Context triple: [Super Bowl XLII, refereeRole, head referee]
-
A.
umpireCrewChief
Indicates that one entity serves as the crew chief (lead umpire) for a particular umpire crew.
-
B.
judicialRole
Indicates that one entity holds or performs a specific official function or position within the judicial system in relation to another entity or legal matter.
-
C.
defensiveRole
Indicates that an entity serves a protective or guarding function in relation to another entity or context.
-
D.
umpires
chosen
Indicates that an entity serves as the umpire overseeing, judging, or officiating an event, activity, or interaction involving another entity.
-
E.
refersToRole
Indicates that one entity designates, mentions, or points to another entity specifically in its capacity as a role or position.
- 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_69a2e8465ef481909655c681b01e2986 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2ef0b6e0c8190ad6a335ee804829c |
completed | Feb. 28, 2026, 1:35 p.m. |
| PD | Predicate disambiguation | batch_69a2eddb98e081909efcf9f0a955a908 |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.