Triple
T22251755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Rat |
E549996
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Patrick O'Neal |
—
|
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: Patrick O'Neal | Statement: [King Rat, stars, Patrick O'Neal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patrick O'Neal Context triple: [King Rat, stars, Patrick O'Neal]
-
A.
Patrick O’Neal
chosen
Patrick O’Neal was an American film, television, and stage actor known for his suave, often sophisticated roles in mid-20th-century Hollywood productions.
-
B.
Gordon Scott
Gordon Scott was an American actor best known for playing Tarzan in a series of popular 1950s and 1960s adventure films.
-
C.
Gordon Scott
Gordon Scott is an editor known for his work on the film "The Doctor and the Devils."
-
D.
Theo Karras
Theo Karras is a fictional character from the Australian-set police procedural television series NCIS: Sydney.
-
E.
Robert Urich
Robert Urich was an American actor best known for his roles in television series such as "Vega$," "Spenser: For Hire," and "Lonesome Dove."
- 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_69e11e41d9408190bd770cf282e22753 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138befa208190877760dec1896740 |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 16, 2026, 8:39 p.m.