Triple
T15346853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arlene Phillips |
E366944
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Arlene Phillips |
E366944
|
NE 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: Arlene Phillips | Statement: [Arlene Phillips, name, Arlene Phillips]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arlene Phillips Context triple: [Arlene Phillips, name, Arlene Phillips]
-
A.
Arlene Phillips
chosen
Arlene Phillips is a British choreographer and television personality best known for her work on stage musicals and as a judge on popular dance competition shows.
-
B.
Phyllis Carlyle
Phyllis Carlyle was a film producer best known for her work on influential 1990s movies, including the psychological thriller "Seven."
-
C.
Arlene Miles
Arlene Miles was the first wife of American jazz singer and songwriter Mel Tormé.
-
D.
Arlene Howell
Arlene Howell is an American actress best known for her role as the secretary Melody Lee Mercer on the television detective series "Bourbon Street Beat."
-
E.
Arlene Gibbs
Arlene Gibbs is a screenwriter best known for co-writing the romantic comedy film "Jumping the Broom."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85a1355608190a6673ddb67231d54 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e1749bc8190a8b9cbcb27288a5b |
completed | April 16, 2026, 1:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb593258081909dcaf2b37fd28e63 |
completed | May 9, 2026, 10:30 p.m. |
Created at: April 10, 2026, 3:17 a.m.