Triple
T20457325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nathan Cohen |
E501824
|
entity |
| Predicate | notableRelative |
P367
|
FINISHED |
| Object | Lorca 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: Lorca Cohen | Statement: [Nathan Cohen, notableRelative, Lorca Cohen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lorca Cohen Context triple: [Nathan Cohen, notableRelative, Lorca Cohen]
-
A.
Lorca Cohen
chosen
Lorca Cohen is the daughter of Canadian singer-songwriter and poet Leonard Cohen, known for maintaining a largely private life outside her father's public artistic legacy.
-
B.
Shalom Cohen
Shalom Cohen was a prominent Sephardic ultra-Orthodox rabbi who served as the leading spiritual authority of the Shas movement in Israel.
-
C.
Nat Cohen
Nat Cohen was a notable member of the British Battalion, recognized for his involvement in the International Brigades during the Spanish Civil War.
-
D.
Don Jakoby
Don Jakoby is an American screenwriter known for his work on science fiction and action films, including contributions to movies like "Blue Thunder" and "Arachnophobia."
-
E.
Christian Gazal
Christian Gazal is a film editor best known for his work on the animated feature "Happy Feet."
- 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.