Triple
T18974081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fred Clark |
E464245
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Benay Venuta |
—
|
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: Benay Venuta | Statement: [Fred Clark, spouse, Benay Venuta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Benay Venuta Context triple: [Fred Clark, spouse, Benay Venuta]
-
A.
Benay Venuta
chosen
Benay Venuta was an American actress, singer, and dancer known for her work in mid-20th-century film, Broadway, and television musicals.
-
B.
Mia Bonzanigo
Mia Bonzanigo is known as a former romantic partner of the Swiss surrealist artist H. R. Giger.
-
C.
Arianna Meloni
Arianna Meloni is an Italian political figure known for her close ties to the right-wing Brothers of Italy party and her marriage to politician Francesco Lollobrigida.
-
D.
Eliana De Santis
Eliana De Santis is an actress known for her role in the French television film "Les Noces rouges."
-
E.
Andrea Fleytas
Andrea Fleytas is a real-life Transocean rig worker and bridge officer whose actions during the 2010 Deepwater Horizon oil rig disaster were later dramatized in the film "Deepwater Horizon."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d61d7728819096f0baea75658a6a |
completed | April 20, 2026, 7:30 a.m. |
Created at: April 10, 2026, noon