Triple
T34604494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | O. J. Berman |
E888557
|
entity |
| Predicate | formerClient |
P133361
|
FINISHED |
| Object | Holly Golightly |
—
|
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: Holly Golightly | Statement: [O. J. Berman, formerClient, Holly Golightly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerClient Context triple: [O. J. Berman, formerClient, Holly Golightly]
-
A.
formerCustom
chosen
Indicates that one entity was previously a customer of another entity but is no longer in that role.
-
B.
formerUser
Indicates that an entity was previously a user of another entity or system but is no longer one.
-
C.
formerLicensee
Indicates that an entity previously held a license from another entity but no longer does.
-
D.
formerBearer
Indicates that an entity previously held or carried something (such as a title, role, or object) but no longer does so.
-
E.
formerPartner
Indicates that one entity was previously in a romantic or partnership relationship with another entity, but that relationship has since ended.
- 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_69f349d489d48190ba30e7d97c6f5ef9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a00144238708190acbec3f791cc873e |
completed | May 10, 2026, 5:14 a.m. |
| PD | Predicate disambiguation | batch_6a00120244a4819090ef39070aba9d99 |
completed | May 10, 2026, 5:05 a.m. |
Created at: May 1, 2026, 2:03 a.m.