Triple
T17429750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cohan family |
E423836
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Helen Costigan Cohan |
—
|
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: Helen Costigan Cohan | Statement: [Cohan family, hasMember, Helen Costigan Cohan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Helen Costigan Cohan Context triple: [Cohan family, hasMember, Helen Costigan Cohan]
-
A.
Nellie Cohan
Nellie Cohan was an American vaudeville performer and the mother of famed entertainer and songwriter George M. Cohan.
-
B.
Josephine Cohan
Josephine Cohan was an American vaudeville performer and actress, best known as the sister of famed entertainer George M. Cohan and a member of the Cohan family theatrical troupe.
-
C.
Eleanor Lambert
Eleanor Lambert is the daughter of American actress Diane Lane and actor Christopher Lambert.
-
D.
Eleanor Lambert
Eleanor Lambert was a pioneering American fashion publicist who played a key role in shaping the modern fashion industry and promoting American designers.
-
E.
Helen Cohan
chosen
Helen Cohan was an American actress and dancer, best known as the daughter of legendary entertainer George M. Cohan and for her appearances in early 20th-century stage and film productions.
- 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e448ffb9c8819099fabfeebdc06883 |
completed | April 19, 2026, 3:16 a.m. |
Created at: April 10, 2026, 5:46 a.m.