Triple
T20120701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ursula Andress |
E490597
|
entity |
| Predicate | notableRole |
P22
|
FINISHED |
| Object | Honey Ryder |
—
|
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: Honey Ryder | Statement: [Ursula Andress, notableRole, Honey Ryder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Honey Ryder Context triple: [Ursula Andress, notableRole, Honey Ryder]
-
A.
Honey Ryder
chosen
Honey Ryder is a fictional Bond girl and shell diver who becomes James Bond’s ally and love interest in the 1962 film "Dr. No."
-
B.
Sally Blane
Sally Blane was an American film actress of the early 20th century who appeared in numerous silent and sound films, often in supporting roles.
-
C.
Louise Hobbs
Louise Hobbs is best known as the wife of British actor and television presenter Tony Robinson.
-
D.
Lara Marlowe
Lara Marlowe is an American-born journalist and longtime foreign correspondent, best known for her reporting from the Middle East and Europe for outlets such as The Irish Times.
-
E.
Lucy McClane
Lucy McClane is the daughter of action hero John McClane in the Die Hard film series, known for her resilience and involvement in her father's high-stakes conflicts.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6673e79dc81908fbd387c067fce79 |
completed | April 20, 2026, 5:49 p.m. |
Created at: April 11, 2026, 11:30 p.m.