Triple
T16721574
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malice |
E406360
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Harold Becker |
E708733
|
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: Harold Becker | Statement: [Malice, director, Harold Becker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harold Becker Context triple: [Malice, director, Harold Becker]
-
A.
Harold Becker
chosen
Harold Becker is an American film director known for character-driven thrillers and dramas such as "Taps," "Sea of Love," and "Malice."
-
B.
Louis Becker
Louis Becker is an architect recognized as a prominent protégé and collaborator of Danish architect Henning Larsen.
-
C.
Frank Beyer
Frank Beyer was a prominent East German film director known for his socially critical and politically charged works produced under the state-owned DEFA studio.
-
D.
Harold Huber
Harold Huber was an American character actor known for his prolific work in 1930s and 1940s Hollywood films, often portraying suave or villainous supporting roles.
-
E.
Joe Becker
Joe Becker is a computer scientist best known as a co-founder of the Unicode Consortium and an early architect of the Unicode character encoding standard.
- 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e38743750c81908a980372ad8f1a6a |
completed | April 18, 2026, 1:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00aaef72fc8190975edfe5076ed9db |
completed | May 10, 2026, 3:57 p.m. |
Created at: April 10, 2026, 5:20 a.m.