Triple
T1271978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bette Davis |
E15728
|
entity |
| Predicate | hasSignatureFeature |
P18678
|
FINISHED |
| Object | distinctive eyes |
—
|
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: distinctive eyes | Statement: [Bette Davis, hasSignatureFeature, distinctive eyes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSignatureFeature Context triple: [Bette Davis, hasSignatureFeature, distinctive eyes]
-
A.
hasSignatureTrait
chosen
Indicates that an entity possesses a defining or characteristic trait that is especially distinctive or representative of it.
-
B.
hasSignatureBit
Indicates that an entity possesses a specific bit or flag used to represent a signature or signed status in a data structure or encoding.
-
C.
hasSignatureRole
Indicates that an entity holds a primary, defining, or officially recognized role within a given context or relationship.
-
D.
hasSignatureVisualStyle
Indicates that an entity is characterized by a distinctive and recognizable visual style that sets it apart from others.
-
E.
hasSign
Indicates that an entity possesses, displays, or is associated with a particular sign or symbol.
- 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_69a4935a94308190bb92555b79032824 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4c06c033081909bc594157abaf5bb |
completed | March 1, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69a4bede52a081909665d60acbe41d31 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:50 p.m.