Triple
T680737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carl Denham |
E13174
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Ann Darrow |
E4506
|
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: Ann Darrow | Statement: [Carl Denham, associatedWith, Ann Darrow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ann Darrow Context triple: [Carl Denham, associatedWith, Ann Darrow]
-
A.
Mary Benedict Cushing
Mary Benedict Cushing was a prominent American socialite from the influential Cushing family, known for her high-profile marriages into wealthy dynasties including that of Vincent Astor.
-
B.
Fay Wray
chosen
Fay Wray was a Canadian-American actress best known for her iconic role as the damsel Ann Darrow in the classic 1933 film "King Kong."
-
C.
Vivian Lake Brady
Vivian Lake Brady is the daughter of NFL quarterback Tom Brady and supermodel Gisele Bündchen.
-
D.
Mary Lee Woods
Mary Lee Woods was a British mathematician and computer scientist who worked on early computers at Ferranti and was the mother of World Wide Web inventor Tim Berners-Lee.
-
E.
Elizabeth Darwin
Elizabeth Darwin is a member of the Darwin family, likely a descendant or relative of the naturalist Charles Darwin.
- 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_69a4933d3bf88190972041cd8cf143b9 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a06e294c8190873116a3253e04f9 |
completed | March 1, 2026, 8:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a5dca153e081908facd835a79da25d |
completed | March 2, 2026, 6:53 p.m. |
Created at: March 1, 2026, 7:36 p.m.