Triple
T3551255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian Dennehy |
E75114
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Judith Scheff
Judith Scheff is best known as the wife of the late American actor Brian Dennehy.
|
E368106
|
NE FINISHED |
How this triple was built (4 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: Judith Scheff | Statement: [Brian Dennehy, spouse, Judith Scheff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Judith Scheff Context triple: [Brian Dennehy, spouse, Judith Scheff]
-
A.
Rachel Elkind
Rachel Elkind is an American music producer and composer best known for her eerie electronic score work with Wendy Carlos, including their influential soundtrack contributions to Stanley Kubrick’s film "The Shining."
-
B.
Roberta Seidman
Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
-
C.
Susan Shaffer Wechsler
Susan Shaffer Wechsler is known as the wife of longtime Arizona senator and 1964 Republican presidential nominee Barry Goldwater.
-
D.
Michael Tronick
Michael Tronick is an American film editor known for his work on numerous major Hollywood productions across several decades.
-
E.
Lori M. Stone
Lori M. Stone is an American politician who serves as the mayor of Warren, Michigan, after previously representing the area in the Michigan House of Representatives.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Judith Scheff Triple: [Brian Dennehy, spouse, Judith Scheff]
Generated description
Judith Scheff is best known as the wife of the late American actor Brian Dennehy.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Judith Scheff Target entity description: Judith Scheff is best known as the wife of the late American actor Brian Dennehy.
-
A.
Rachel Elkind
Rachel Elkind is an American music producer and composer best known for her eerie electronic score work with Wendy Carlos, including their influential soundtrack contributions to Stanley Kubrick’s film "The Shining."
-
B.
Roberta Seidman
Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
-
C.
Susan Shaffer Wechsler
Susan Shaffer Wechsler is known as the wife of longtime Arizona senator and 1964 Republican presidential nominee Barry Goldwater.
-
D.
Michael Tronick
Michael Tronick is an American film editor known for his work on numerous major Hollywood productions across several decades.
-
E.
Lori M. Stone
Lori M. Stone is an American politician who serves as the mayor of Warren, Michigan, after previously representing the area in the Michigan House of Representatives.
- F. None of above. chosen
Provenance (5 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_69ad85d33c6c819081d5ac1df13b5680 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbfd52f44819088e07139fe987e2a |
completed | March 8, 2026, 6:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b38bec437c8190b35ca77dc19d441d |
completed | March 13, 2026, 4 a.m. |
| NEDg | Description generation | batch_69b38c5d9ec8819095132a06c1add128 |
completed | March 13, 2026, 4:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b38cc3f330819096df64a81d4a5f58 |
completed | March 13, 2026, 4:04 a.m. |
Created at: March 8, 2026, 3:20 p.m.