Triple
T22768395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iris |
E563186
|
entity |
| Predicate | notableCostumeItem |
P28106
|
FINISHED |
| Object | wide-brimmed hat |
—
|
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: wide-brimmed hat | Statement: [Iris, notableCostumeItem, wide-brimmed hat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableCostumeItem Context triple: [Iris, notableCostumeItem, wide-brimmed hat]
-
A.
costume
Indicates that one entity is wearing, dressed in, or outfitted with the other entity as a costume.
-
B.
notableOutfit
Indicates that an entity is known for or associated with wearing a particular outfit or style of clothing.
-
C.
costumeDesignNotability
Indicates that an entity is notable or recognized specifically for its work or achievements in costume design.
-
D.
costumeFeatures
Indicates that a costume possesses or includes specific features, attributes, or decorative elements.
-
E.
costumeElement
chosen
Indicates that one item functions as a component or part of another item's 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17b59c9cc8190a6edd68f3209a672 |
completed | April 29, 2026, 3:30 a.m. |
| PD | Predicate disambiguation | batch_69eed2b88d88819096015deb6a648801 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:27 p.m.