Triple
T18238246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irwin Unger |
E436736
|
entity |
| Predicate | coAuthor |
P398
|
FINISHED |
| Object | Debi Unger |
—
|
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: Debi Unger | Statement: [Irwin Unger, coAuthor, Debi Unger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Debi Unger Context triple: [Irwin Unger, coAuthor, Debi Unger]
-
A.
Debi Unger
chosen
Debi Unger is a writer and historian known for co-authoring several works of American history, often in collaboration with her husband, historian Irwin Unger.
-
B.
Debra Weinfeld
Debra Weinfeld is a film editor known for her work on the action drama movie "Never Back Down."
-
C.
Debra Frisch
Debra Frisch is an American former psychology professor and blogger best known for a high-profile online harassment case involving a political commentator.
-
D.
Deborah Kara Unger
Deborah Kara Unger is a Canadian actress known for her intense, often edgy performances in films such as "Crash," "The Game," and "Silent Hill."
-
E.
Diane Siegler
Diane Siegler is a character in the satirical film "Citizen Ruth," which critiques the abortion debate in the United States.
- 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_69d8b91104e08190a8241f7d260a5162 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4f7e0a0ac819090d48ae45b1ebfc9 |
completed | April 19, 2026, 3:42 p.m. |
Created at: April 10, 2026, 10:33 a.m.