Triple
T12893923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Sullivan |
E308441
|
entity |
| Predicate | visualSignature |
P51216
|
FINISHED |
| Object | trench coat and fedora |
—
|
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: trench coat and fedora | Statement: [Michael Sullivan, visualSignature, trench coat and fedora]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualSignature Context triple: [Michael Sullivan, visualSignature, trench coat and fedora]
-
A.
signatureImage
Indicates that an entity has an associated image that visually represents its signature.
-
B.
signatureVehicle
Indicates that the vehicle is the primary or characteristic mode of transportation associated with a particular entity (such as a person, group, or brand).
-
C.
signatureFeature
chosen
Indicates that one entity is a defining or characteristic feature that distinctly identifies or typifies another entity.
-
D.
signatureVariant
Indicates that one signature is an alternative or modified form of another signature, differing in some aspect such as content, format, or representation while remaining related.
-
E.
signatureWork
Indicates that the work is a defining or most representative creation associated with an entity (such as a person, group, 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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d971484aa08190a8adfafabe600903 |
completed | April 10, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69d96fa776648190b9b5c30722ea50b6 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:40 p.m.