Triple
T10856007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Van Cleef |
E256270
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Clarence |
E151400
|
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: Clarence | Statement: [Lee Van Cleef, givenName, Clarence]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clarence Context triple: [Lee Van Cleef, givenName, Clarence]
-
A.
Clarence
chosen
Clarence is a masculine given name of Latin origin, commonly used in English-speaking countries.
-
B.
Clarence Rivers
Clarence Rivers was an influential American Catholic priest, composer, and liturgist known for pioneering the integration of African-American musical traditions into Catholic worship.
-
C.
King Richard
"King Richard" is a 2021 biographical sports drama film about Richard Williams, the determined father and coach of tennis champions Venus and Serena Williams.
-
D.
Henry
Henry is the central protagonist of the video game "Gray Matter," around whom the story’s mystery and events revolve.
-
E.
Henry
Henry is the disturbed serial killer protagonist of the cult horror film "Henry: Portrait of a Serial Killer," portrayed by Michael Rooker.
- 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_69d6aa83d1448190a66d93c32394d21f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7513695ac8190b5812e977a422c37 |
completed | April 9, 2026, 7:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69deb197808c8190b1c80aeb2144a909 |
completed | April 14, 2026, 9:28 p.m. |
Created at: April 8, 2026, 9:20 p.m.