Triple
T26809886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diamonds and Sapphires |
E671957
|
entity |
| Predicate | hasCelebrityEndorser |
P146142
|
FINISHED |
| Object | Elizabeth Taylor |
—
|
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: Elizabeth Taylor | Statement: [Diamonds and Sapphires, hasCelebrityEndorser, Elizabeth Taylor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCelebrityEndorser Context triple: [Diamonds and Sapphires, hasCelebrityEndorser, Elizabeth Taylor]
-
A.
fashionBrandEndorsement
Indicates a relationship where a fashion brand formally supports, promotes, or is publicly associated with an entity (such as a person, product, or event) as an endorser.
-
B.
brandEndorsement
Indicates that one entity publicly supports, recommends, or promotes another entity’s brand, product, or service.
-
C.
hasNotablePersonAsFace
Indicates that an entity is publicly represented or symbolized by a specific notable person, such as a spokesperson, ambassador, or brand face.
-
D.
hasNotablePersonConnection
Indicates that there exists a significant or noteworthy personal, professional, or historical relationship between the subject and the referenced person.
-
E.
hasNotableEndorsement
chosen
Indicates that an entity is publicly supported or recommended by a notable or influential individual, organization, or group.
- 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_69eeb3225a3c8190aaf6746efeded2f3 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f68805b4848190b75da14996d52a38 |
completed | May 2, 2026, 11:25 p.m. |
| PD | Predicate disambiguation | batch_69f68609c0b08190a8e1238a4d97c270 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 27, 2026, 4:28 a.m.