Triple
T25453031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | East Bengal FC |
E637837
|
entity |
| Predicate | homeCityRivalry |
P46046
|
FINISHED |
| Object | Kolkata Derby with Mohun Bagan |
—
|
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: Kolkata Derby with Mohun Bagan | Statement: [East Bengal FC, homeCityRivalry, Kolkata Derby with Mohun Bagan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeCityRivalry Context triple: [East Bengal FC, homeCityRivalry, Kolkata Derby with Mohun Bagan]
-
A.
cityRivalry
Indicates a competitive or adversarial relationship that exists between two cities, often involving sports, economics, culture, or historical tensions.
-
B.
homeCityOfRivalTeam
Indicates the city that serves as the home base for a team’s rival.
-
C.
rivalryInvolvesCity
chosen
Indicates that a rivalry relationship includes or is associated with a particular city as one of its involved locations.
-
D.
hasLocalRivalry
Indicates that there is an ongoing competitive or adversarial relationship between entities that are geographically close or share the same local area.
-
E.
countryOfRivalry
Indicates that one entity is a country with which another entity has a relationship of rivalry or adversarial competition.
- 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_69e75db7c5048190b8da9cd7eeedb610 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f70885cc81909f1574406d67c682 |
completed | May 2, 2026, 1:07 p.m. |
| PD | Predicate disambiguation | batch_69f5afd5baac8190bb8ed576813c8591 |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 21, 2026, 2:03 p.m.