Triple
T6545123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl XXXI |
E150985
|
entity |
| Predicate | hostCitySuperBowlNumber |
P44826
|
FINISHED |
| Object | New Orleans ninth Super Bowl as host |
—
|
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: New Orleans ninth Super Bowl as host | Statement: [Super Bowl XXXI, hostCitySuperBowlNumber, New Orleans ninth Super Bowl as host]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostCitySuperBowlNumber Context triple: [Super Bowl XXXI, hostCitySuperBowlNumber, New Orleans ninth Super Bowl as host]
-
A.
hostCityNumberOfSuperBowlsHosted
chosen
Indicates the number of Super Bowl games that have been hosted in a particular city.
-
B.
hostCityFirstSuperBowl
Indicates the city that hosted a team's first Super Bowl appearance.
-
C.
SuperBowlCity
Indicates that a city is the host location for a particular Super Bowl event.
-
D.
superBowlChampionWith
Indicates that one entity is the Super Bowl champion associated with the other entity (such as a specific season, year, or team).
-
E.
wonSuperBowlWith
Indicates that one entity (typically a player, coach, or team member) achieved a Super Bowl victory while being part of a specific 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_69c687f3fd60819083bfa583e5bcfa71 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ce07332481909a5a7964282eb776 |
completed | March 27, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69c6acf3e3708190b052ec774e607cb7 |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:50 p.m.