Triple
T22002612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maureen O'Sullivan |
E543367
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Patrick Farrow |
—
|
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: Patrick Farrow | Statement: [Maureen O'Sullivan, child, Patrick Farrow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patrick Farrow Context triple: [Maureen O'Sullivan, child, Patrick Farrow]
-
A.
Patrick Farrow
chosen
Patrick Farrow was an American sculptor and artist, and the son of film director John Farrow and actress Maureen O'Sullivan.
-
B.
Joe Farrow
Joe Farrow is a law enforcement official best known for leading the California Highway Patrol as its commissioner.
-
C.
Stephanie Farrow
Stephanie Farrow is an American actress and model best known as the younger sister of actress Mia Farrow.
-
D.
Dean Andrews
Dean Andrews is an English actor best known for his television work, including prominent roles in British drama series such as Life on Mars.
-
E.
Griffin Dunne
Griffin Dunne is an American actor, director, and producer known for roles in films like "An American Werewolf in London" and "After Hours."
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1276bf2a48190910d9c27f1c5e74f |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:20 p.m.