Triple
T20343367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Magic Flame |
E495798
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Agnes Ayres |
—
|
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: Agnes Ayres | Statement: [The Magic Flame, hasCastMember, Agnes Ayres]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Agnes Ayres Context triple: [The Magic Flame, hasCastMember, Agnes Ayres]
-
A.
Agnes Ayres
chosen
Agnes Ayres was an American silent film actress best known for her leading role opposite Rudolph Valentino in the 1921 romantic drama "The Sheik."
-
B.
Agnes Yorke
Agnes Yorke is the daughter of Radiohead frontman Thom Yorke.
-
C.
Agnes Carre
Agnes Carre was the wife of Scottish judge, philosopher, and agricultural improver Henry Home, Lord Kames, and a member of the 18th-century Scottish gentry.
-
D.
Agnes Hay
Agnes Hay was the wife of Australian explorer William Christie Gosse, known primarily through her association with his life and work.
-
E.
Agnes Hathaway
Agnes Hathaway is a central character in Maggie O’Farrell’s novel "Hamnet," portrayed as William Shakespeare’s enigmatic and resilient wife.
- 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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67836b72081908be65115abdb37bf |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:24 a.m.