Triple
T20702091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milk (2008 film) |
E508808
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | Dan White |
—
|
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: Dan White | Statement: [Milk (2008 film), character, Dan White]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dan White Context triple: [Milk (2008 film), character, Dan White]
-
A.
Dan White
chosen
Dan White was a former San Francisco city supervisor best known for assassinating Mayor George Moscone and fellow supervisor Harvey Milk in 1978.
-
B.
Richard Speck
Richard Speck was an American mass murderer infamous for the 1966 killings of eight student nurses in Chicago.
-
C.
Charles Starkweather
Charles Starkweather was a 1950s American spree killer whose notorious murder rampage with his teenage girlfriend inspired numerous films and fictional characters.
-
D.
Mark Chapman
Mark Chapman is a British sports broadcaster best known for his work presenting football coverage on BBC television and radio.
-
E.
James Carroll Beckwith
James Carroll Beckwith was an American portrait and genre painter of the late 19th and early 20th centuries, known for his refined academic style and contributions to the New York art scene.
- 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_69e0b4c2b2a481909e31e9cb8f81ab55 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c18cb9cc819095d0669dca037424 |
completed | April 21, 2026, 12:15 a.m. |
Created at: April 16, 2026, 12:12 p.m.