Triple
T37840827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norman Hartnell (vintage gown loaned by Queen Elizabeth II) |
E943469
|
entity |
| Predicate | couturier |
P189262
|
FINISHED |
| Object | Sir Norman Hartnell |
—
|
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: Sir Norman Hartnell | Statement: [Norman Hartnell (vintage gown loaned by Queen Elizabeth II), couturier, Sir Norman Hartnell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: couturier Context triple: [Norman Hartnell (vintage gown loaned by Queen Elizabeth II), couturier, Sir Norman Hartnell]
-
A.
tailors
Indicates that one entity customizes, adapts, or modifies something specifically to suit the needs, characteristics, or preferences of another entity.
-
B.
stylingHouse
Indicates a relationship where a house is being designed, decorated, or otherwise given a particular aesthetic style.
-
C.
designerAlias
Indicates that one name or label is used as an alternative alias for a designer.
-
D.
madeÉtoileBy
Indicates that something was created or produced by an entity named Étoile.
-
E.
closedCoutureHouse
Indicates that a couture fashion house has ceased operations or been formally closed.
- 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_69f76eeb0f7081908d6d3adbc469889c |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbbae559a8819086ef839973f8d9b2 |
completed | May 6, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69fbb1440fa08190abf25ba684f75b6e |
completed | May 6, 2026, 9:23 p.m. |
| PDg | Predicate description generation | batch_69fbbae3fc508190adff3d7abbf107a4 |
completed | May 6, 2026, 10:04 p.m. |
Created at: May 3, 2026, 4:19 p.m.