Triple
T22297822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tara Elders |
E551168
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Tara Elders |
—
|
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: Tara Elders | Statement: [Tara Elders, name, Tara Elders]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tara Elders Context triple: [Tara Elders, name, Tara Elders]
-
A.
Tara Elders
chosen
Tara Elders is a Dutch actress known for her roles in film and television, including collaborations with director Theo van Gogh.
-
B.
Tara Wilson
Tara Wilson is a fictional attorney and main character from the television series "Boston Legal," known for her intelligence, ambition, and complex personal relationships within the law firm.
-
C.
Tara Wilson
Tara Wilson is a Canadian-born actress and former model best known as the wife of "Sex and the City" actor Chris Noth.
-
D.
Tara Rushton
Tara Rushton is an Australian sports presenter and journalist best known for her work covering football and rugby league on television.
-
E.
Tara Martin
Tara Martin is a fictional character from the soap opera "All My Children," known as one of the early members of the Martin family.
- 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_69e11e45fb848190a1b2ae21296e3a5f |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1572200c88190b9413286136fef15 |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:41 p.m.