Triple
T23674005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2012 NCAA Division I men's basketball tournament |
E584815
|
entity |
| Predicate | seedOfDuke |
P152939
|
FINISHED |
| Object | 2 |
—
|
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: 2 | Statement: [2012 NCAA Division I men's basketball tournament, seedOfDuke, 2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seedOfDuke Context triple: [2012 NCAA Division I men's basketball tournament, seedOfDuke, 2]
-
A.
lastDukeBeforeKingship
Indicates that the subject was the final holder of the ducal title immediately prior to the establishment or assumption of kingship.
-
B.
seedOfLoser
Indicates that one entity is the origin, cause, or initial source leading to another entity’s failure or loss.
-
C.
reignAsDukeFrom
Indicates that an entity holds and exercises the title and authority of duke over a domain starting from a specified time.
-
D.
seedOfWinner
Indicates that one entity is the seed or ranking position assigned to the entity that wins a competition or match.
-
E.
仕えた君主
Indicates a relationship where someone served or was in the service of a particular lord or sovereign.
- F. None of above. chosen
Provenance (4 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_69e24901421881908c17a5293bdd4a8e |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b4f1dee08190bfe78564c65f01ad |
completed | April 29, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f118dd13008190a8799b4e9cadbd79 |
completed | April 28, 2026, 8:30 p.m. |
| PDg | Predicate description generation | batch_69f121cc494081908c987adfcde89b0e |
completed | April 28, 2026, 9:08 p.m. |
Created at: April 17, 2026, 6:51 p.m.