Triple
T23458568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack Geller |
E568001
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Judy Geller |
—
|
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: Judy Geller | Statement: [Jack Geller, relative, Judy Geller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Judy Geller Context triple: [Jack Geller, relative, Judy Geller]
-
A.
Judy Geller
chosen
Judy Geller is a recurring character on the TV show "Friends," known as the often critical and overbearing mother of Monica and Ross Geller.
-
B.
Margalo Gillmore
Margalo Gillmore was an English-born American stage and film actress known for her sophisticated supporting roles in Broadway productions and classic Hollywood films of the mid-20th century.
-
C.
Sandy Cohen
Sandy Cohen is best known as the wife of the late American actor Danny Aiello.
-
D.
Sandy Cohen
Sandy Cohen is a principled public defender and devoted father on the television drama "The O.C.," known for his moral compass, wit, and central role in the Cohen family.
-
E.
Josie Geller
Josie Geller is the awkward but determined copy editor who goes undercover as a high school student in the romantic comedy film "Never Been Kissed."
- 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_69e2458b4c888190b1d7998f9862a558 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a699c0088190a84d7a495a3e3d61 |
completed | April 29, 2026, 6:35 a.m. |
Created at: April 17, 2026, 5:53 p.m.