Triple
T21247183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julie Harris |
E523641
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | "Darling" |
—
|
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: "Darling" | Statement: [Julie Harris, workedOn, "Darling"]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: "Darling" Context triple: [Julie Harris, workedOn, "Darling"]
-
A.
Darling
Darling is a surname most prominently associated with Ron Darling, a former Major League Baseball pitcher and current television baseball analyst.
-
B.
Darling
Darling is a residential suburb in Melbourne, Victoria, known for its local train station on the Glen Waverley railway line and its proximity to the city.
-
C.
Darling
Darling is the kind, affectionate human owner of Lady in Disney's animated film "Lady and the Tramp."
-
D.
Darling
chosen
Darling is a 1965 British drama film directed by John Schlesinger, known for its incisive portrayal of a young woman's rise in London's high society and for winning multiple Academy Awards.
-
E.
Darling
Darling is a character played by Eiza González in the action film "Baby Driver," known as a stylish and dangerous bank robber and the girlfriend of fellow criminal Buddy.
- 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_69e0b5146c108190adc9adb73e90abff |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7359abdac81908b74dad1b8cc0aa9 |
completed | April 21, 2026, 8:30 a.m. |
Created at: April 16, 2026, 3:54 p.m.