Triple
T7024906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Married a Witch |
E162918
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Susan Hayward |
E524744
|
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: Susan Hayward | Statement: [I Married a Witch, starring, Susan Hayward]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Susan Hayward Context triple: [I Married a Witch, starring, Susan Hayward]
-
A.
Susan Hayward
chosen
Susan Hayward was an American film actress known for her intense dramatic performances and Academy Award–winning role in "I Want to Live!" (1958).
-
B.
Linda Harrison
Linda Harrison is an American actress best known for her role as Nova in the original "Planet of the Apes" films.
-
C.
Anne Francis
Anne Francis was an American actress best known for her roles in films like "Forbidden Planet" and the TV series "Honey West," for which she received Emmy and Golden Globe nominations.
-
D.
Sylvia Sidney
Sylvia Sidney was an American actress known for her work in 1930s crime dramas and later roles in films like "Beetlejuice" and "Mars Attacks!".
-
E.
Anne Gwynne
Anne Gwynne was a popular American film and television actress of the 1940s, often remembered as one of the earliest "scream queens" in horror cinema.
- 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_69c6885b26248190a857541e3d10e299 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e1fb8f0c8190b15dd7ce7ab6a8f2 |
completed | March 27, 2026, 8 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8ac7b53488190a00978e936b563ac |
completed | March 29, 2026, 4:37 a.m. |
Created at: March 27, 2026, 2:35 p.m.