Triple
T21510976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bette Davis as Leslie Crosbie |
E530717
|
entity |
| Predicate | keyProp |
P7606
|
FINISHED |
| Object | incriminating letter |
—
|
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: incriminating letter | Statement: [Bette Davis as Leslie Crosbie, keyProp, incriminating letter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyProp Context triple: [Bette Davis as Leslie Crosbie, keyProp, incriminating letter]
-
A.
keyProponent
Indicates that the subject is a primary supporter, advocate, or driving force behind the object.
-
B.
keyOf
Indicates that one entity functions as the key (identifier or access token) associated with another entity.
-
C.
keyAttribute
Indicates that the specified attribute is a primary or defining characteristic that uniquely identifies or is essential to the entity within a given context.
-
D.
key
chosen
Indicates that one entity functions as a key (literal or metaphorical) that unlocks, enables access to, or provides a crucial solution or control over another entity.
-
E.
keyField
Indicates that the referenced field serves as a primary or unique identifier within a data structure or record.
- 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea863b18819080e3ff249b10ec28 |
completed | April 23, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69e6320043bc81909417c41a718652ba |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:25 p.m.