Triple
T9039145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annie Leibovitz |
E216574
|
entity |
| Predicate | datePartneredWith |
P32390
|
FINISHED |
| Object | circa 1989 (Susan Sontag) |
—
|
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: circa 1989 (Susan Sontag) | Statement: [Annie Leibovitz, datePartneredWith, circa 1989 (Susan Sontag)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: datePartneredWith Context triple: [Annie Leibovitz, datePartneredWith, circa 1989 (Susan Sontag)]
-
A.
laterPartnerInPracticeWith
Indicates that one entity became a partner in professional practice with another entity at a later point in time.
-
B.
relationshipStartYear
chosen
Indicates the calendar year in which a particular relationship between entities was initiated.
-
C.
partnerInActWith
Indicates that two or more entities jointly participate as partners in carrying out the same act or action.
-
D.
hasPartner
Indicates that one entity is in a partner relationship (such as romantic, life, or business partnership) with another entity.
-
E.
partnerInMusicDuoWith
Indicates that two entities are members of the same musical duo, performing together as a two-person act.
- 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_69ca83d22d488190adbce5e020e9cd1d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6ac46f4881909882403bb81db152 |
completed | April 1, 2026, 12:45 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee3597c81908919cf866ae95c24 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:09 p.m.