Triple
T8795728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arena Castelão |
E209283
|
entity |
| Predicate | stateStadiumRanking |
P67849
|
FINISHED |
| Object | largest stadium in Ceará |
—
|
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: largest stadium in Ceará | Statement: [Arena Castelão, stateStadiumRanking, largest stadium in Ceará]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stateStadiumRanking Context triple: [Arena Castelão, stateStadiumRanking, largest stadium in Ceará]
-
A.
associatedStadiums
Indicates that there is a relationship linking an entity to one or more stadiums with which it is connected or affiliated.
-
B.
stadiumFor
Indicates that a particular stadium serves as the designated home or primary venue for a specific team, event, or organization.
-
C.
oneOfLargestStadiumsByCapacity
chosen
Indicates that a stadium is among the largest in a given set or region when ranked by seating capacity.
-
D.
stadium
Indicates that an entity is a sports or event venue where games, competitions, or large gatherings take place.
-
E.
homeStadiumOf
Indicates that a particular stadium serves as the primary home venue for a specific sports team or organization.
- 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_69ca836240888190a62b262e56a69d2f |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5fa24ca08190a7738a7f1c446456 |
completed | March 31, 2026, 11:58 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1d48f08190b325a77d4c76d223 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:44 p.m.