Triple
T22537026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Long Red |
E557181
|
entity |
| Predicate | performedBy |
P1363
|
FINISHED |
| Object | Corky Laing |
—
|
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: Corky Laing | Statement: [Long Red, performedBy, Corky Laing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Corky Laing Context triple: [Long Red, performedBy, Corky Laing]
-
A.
Corky Laing
chosen
Corky Laing is a Canadian rock drummer best known as a longtime member of the hard rock band Mountain.
-
B.
John Mac McMurphy
John "Mac" McMurphy is an editor known for his work on the film "Wild."
-
C.
Randle Patrick McMurphy
Randle Patrick McMurphy is a rebellious, charismatic patient in a mental institution whose defiance against authoritarian control drives the central conflict of *One Flew Over the Cuckoo's Nest*.
-
D.
Colleen McMurphy
Colleen McMurphy is a compassionate yet resilient Army nurse and central character in the television drama "China Beach," set during the Vietnam War.
-
E.
Richard Dysart
Richard Dysart was an American actor best known for his Emmy-winning role as attorney Leland McKenzie on the television series "L.A. Law."
- 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15edbd1ec81908ef26b9e442d1921 |
completed | April 29, 2026, 1:29 a.m. |
Created at: April 16, 2026, 8:51 p.m.