Triple
T18537362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Murphy |
E452998
|
entity |
| Predicate | hasSpouse |
P13
|
FINISHED |
| Object | Connie Murphy |
—
|
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: Connie Murphy | Statement: [Steve Murphy, hasSpouse, Connie Murphy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Connie Murphy Context triple: [Steve Murphy, hasSpouse, Connie Murphy]
-
A.
Connie Murphy
chosen
Connie Murphy is the wife of retired DEA agent Steve Murphy, known for his role in the pursuit of Colombian drug lord Pablo Escobar.
-
B.
Colleen Murphy
Colleen Murphy is a Canadian playwright, filmmaker, and librettist renowned for her powerful, emotionally intense stage works.
-
C.
Connie McInerny
Connie McInerny was the wife of American philosopher and novelist Ralph McInerny.
-
D.
Bridget Moynahan
Bridget Moynahan is an American actress and model best known for her roles in films like "Coyote Ugly" and "I, Robot" and the TV series "Blue Bloods."
-
E.
Cynthia Murphy
Cynthia Murphy is a central maternal character in the musical "Dear Evan Hansen," known as the caring but emotionally strained mother of Connor and Zoe Murphy.
- 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_69d8d387b5548190aa030dad2cb4947e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e534030bd88190b25b95305a12a0c1 |
completed | April 19, 2026, 7:58 p.m. |
Created at: April 10, 2026, 11:37 a.m.