Triple
T26989322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miss Universe 1985 |
E679822
|
entity |
| Predicate | bestNationalCostume |
P36457
|
FINISHED |
| Object | Yuko Yamaguchi |
—
|
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: Yuko Yamaguchi | Statement: [Miss Universe 1985, bestNationalCostume, Yuko Yamaguchi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bestNationalCostume Context triple: [Miss Universe 1985, bestNationalCostume, Yuko Yamaguchi]
-
A.
nationalDress
Indicates that an item of clothing is recognized as the traditional or customary dress associated with a particular nation or culture.
-
B.
bestCostumeDesignWinner
chosen
Indicates that the subject is the winner of an award or recognition for best costume design in a given context or event.
-
C.
traditionalDressVariant
Indicates that one traditional dress is a variant or localized form of another traditional dress within the same broader cultural or stylistic tradition.
-
D.
bestCostumeDesignColor
Indicates that an entity received or is associated with an award for best costume design in a color film or color category.
-
E.
costume
Indicates that one entity is wearing, dressed in, or outfitted with the other entity as a costume.
- 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_69eeeb5138ac8190b3c273ddc659a54f |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6218de4ec81908d3001e5b8748c7d |
completed | May 2, 2026, 4:08 p.m. |
| PD | Predicate disambiguation | batch_69f611b07a808190af7c704bbdfe0587 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:50 a.m.