Triple
T7567253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellen Burstyn |
E178946
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Paul Roberts
Paul Roberts is known primarily as a former husband of acclaimed American actress Ellen Burstyn.
|
E677625
|
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: Paul Roberts | Statement: [Ellen Burstyn, spouse, Paul Roberts]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Roberts Context triple: [Ellen Burstyn, spouse, Paul Roberts]
-
A.
Jonathan Roberts
Jonathan Roberts is an American screenwriter best known for co-writing Disney’s animated classic "The Lion King."
-
B.
Ian Roberts
Ian Roberts is a South African actor best known for his roles in film, television, and stage productions, often portraying rugged or authoritative characters.
-
C.
Paul Rogers
Paul Rogers is an American film editor best known for his Academy Award–winning work on the multiverse film "Everything Everywhere All at Once."
-
D.
Brian Fawcett
Brian Fawcett was the son of British explorer Percy Fawcett, known mainly for his connection to his father's legendary Amazon expeditions and disappearance.
-
E.
William Roberts
William Roberts was an American screenwriter best known for writing the screenplay for the classic Western film "The Magnificent Seven" (1960).
- 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: Paul Roberts Triple: [Ellen Burstyn, spouse, Paul Roberts]
Generated description
Paul Roberts is known primarily as a former husband of acclaimed American actress Ellen Burstyn.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Paul Roberts Target entity description: Paul Roberts is known primarily as a former husband of acclaimed American actress Ellen Burstyn.
-
A.
Jonathan Roberts
Jonathan Roberts is an American screenwriter best known for co-writing Disney’s animated classic "The Lion King."
-
B.
Ian Roberts
Ian Roberts is a South African actor best known for his roles in film, television, and stage productions, often portraying rugged or authoritative characters.
-
C.
Paul Rogers
Paul Rogers is an American film editor best known for his Academy Award–winning work on the multiverse film "Everything Everywhere All at Once."
-
D.
Brian Fawcett
Brian Fawcett was the son of British explorer Percy Fawcett, known mainly for his connection to his father's legendary Amazon expeditions and disappearance.
-
E.
William Roberts
William Roberts was an American screenwriter best known for writing the screenplay for the classic Western film "The Magnificent Seven" (1960).
- 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_69c69f2f80288190b95cceb4da92ab2b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f91c717881909c88901cc3b101c7 |
completed | March 27, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c870780d24819095196cd3a22bec5a |
completed | March 29, 2026, 12:21 a.m. |
| NEDg | Description generation | batch_69c8725e42a481909bf442987fca3a8c |
completed | March 29, 2026, 12:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c872f89ff08190809d476ae6809488 |
completed | March 29, 2026, 12:31 a.m. |
Created at: March 27, 2026, 3:51 p.m.