Triple
T19358844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tony Rome |
E484222
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Gordon Douglas |
—
|
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: Gordon Douglas | Statement: [Tony Rome, director, Gordon Douglas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gordon Douglas Context triple: [Tony Rome, director, Gordon Douglas]
-
A.
Gordon Douglas
chosen
Gordon Douglas was an American film director known for his prolific work across genres in Hollywood from the 1930s through the 1970s.
-
B.
Lloyd Taylor
Lloyd Taylor was an architect known for designing Parliament House in Adelaide, South Australia.
-
C.
Lloyd Taylor
Lloyd Taylor is a screenwriter best known for his work on the animated spy comedy film "Spies in Disguise."
-
D.
George Aldrich
George Aldrich is a NASA contamination control specialist known for his long career testing materials for off-gassing to ensure astronaut safety on space missions.
-
E.
Robert Gardner
Robert Gardner is an American documentary filmmaker and anthropologist best known for his influential ethnographic films such as "Dead Birds" and "Forest of Bliss."
- 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_69d8e8d305088190ad13571532aa454c |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e6190a1ec88190ba6d2d45174dc85a |
completed | April 20, 2026, 12:16 p.m. |
Created at: April 10, 2026, 1:34 p.m.