Triple
T20457326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leonard Cohen |
E501824
|
entity |
| Predicate | notableRelative |
P367
|
FINISHED |
| Object | Nathan Cohen |
—
|
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: Nathan Cohen | Statement: [Leonard Cohen, notableRelative, Nathan Cohen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nathan Cohen Context triple: [Leonard Cohen, notableRelative, Nathan Cohen]
-
A.
Nathan Cohen
chosen
Nathan Cohen is the paternal grandfather of Lorca Cohen, the daughter of renowned Canadian singer-songwriter Leonard Cohen.
-
B.
Jake Cohen
Jake Cohen is known primarily as the son of Michael Cohen, the former personal attorney to Donald Trump.
-
C.
Matt Cohen
Matt Cohen is an American actor best known for his roles on television series such as "Supernatural" and "General Hospital," as well as appearances in various films.
-
D.
Nathan Grossman
Nathan Grossman is a Swedish documentary filmmaker best known for directing the climate activist portrait film "I Am Greta."
-
E.
Nathan Orloff
Nathan Orloff is a film editor known for his work on high-profile action movies, including the John Wick franchise.
- 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_69e0b4ad4940819098cf2ff6413574e5 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e696a2a8a88190992211b09295d8ea |
completed | April 20, 2026, 9:12 p.m. |
Created at: April 16, 2026, 11:33 a.m.