Triple
T21229765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Body of Evidence |
E523176
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Anne Archer |
—
|
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: Anne Archer | Statement: [Body of Evidence, starring, Anne Archer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anne Archer Context triple: [Body of Evidence, starring, Anne Archer]
-
A.
Anne Archer
chosen
Anne Archer is an American actress best known for her Academy Award–nominated role in the 1987 thriller "Fatal Attraction."
-
B.
Mary Archer
Mary Archer is a British scientist and academic, known for her work in solar energy research and for being married to novelist and former politician Jeffrey Archer.
-
C.
Amy Archer
Amy Archer is a fast-talking, sharp-witted investigative reporter in the film "The Hudsucker Proxy" who uncovers corporate corruption.
-
D.
Rachel Greer
Rachel Greer is a professional known for her expertise in Amazon marketplace compliance, product safety, and e-commerce consulting.
-
E.
Rosemary Woodruff
Rosemary Woodruff was an American counterculture figure and activist best known for her involvement in the 1960s psychedelic movement alongside Timothy Leary.
- 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_69e0b512ad94819087942b2ed925185f |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e734ae60408190a9480b27d109b8fc |
completed | April 21, 2026, 8:26 a.m. |
Created at: April 16, 2026, 3:45 p.m.