Triple
T611887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carol Burnett |
E12115
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Don Saroyan
Don Saroyan was an American actor and television producer best known for his marriage to comedian and actress Carol Burnett.
|
E92546
|
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: Don Saroyan | Statement: [Carol Burnett, spouse, Don Saroyan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Don Saroyan Context triple: [Carol Burnett, spouse, Don Saroyan]
-
A.
Leo Tover
Leo Tover was an American cinematographer known for his work on numerous classic Hollywood films across several decades.
-
B.
Richard Leibler
Richard Leibler was an American mathematician and statistician best known for co-developing the Kullback–Leibler divergence, a fundamental concept in information theory and statistics.
-
C.
Neil Meron
Neil Meron is an American film and television producer best known for his work on acclaimed musical adaptations and award-winning projects such as "Chicago."
-
D.
Norman Lloyd
Norman Lloyd was an American actor, producer, and director whose career in film, television, and theater spanned more than eight decades.
-
E.
Tom Benedek
Tom Benedek is an American screenwriter best known for co-writing the science fiction film "Cocoon."
- 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: Don Saroyan Triple: [Carol Burnett, spouse, Don Saroyan]
Generated description
Don Saroyan was an American actor and television producer best known for his marriage to comedian and actress Carol Burnett.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Don Saroyan Target entity description: Don Saroyan was an American actor and television producer best known for his marriage to comedian and actress Carol Burnett.
-
A.
Leo Tover
Leo Tover was an American cinematographer known for his work on numerous classic Hollywood films across several decades.
-
B.
Richard Leibler
Richard Leibler was an American mathematician and statistician best known for co-developing the Kullback–Leibler divergence, a fundamental concept in information theory and statistics.
-
C.
Neil Meron
Neil Meron is an American film and television producer best known for his work on acclaimed musical adaptations and award-winning projects such as "Chicago."
-
D.
Norman Lloyd
Norman Lloyd was an American actor, producer, and director whose career in film, television, and theater spanned more than eight decades.
-
E.
Tom Benedek
Tom Benedek is an American screenwriter best known for co-writing the science fiction film "Cocoon."
- 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_69a493309df48190a327f748e88049a6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49e07739481909930a6577c081b9e |
completed | March 1, 2026, 8:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a6732a8c0881909753261f9256fcf2 |
completed | March 3, 2026, 5:35 a.m. |
| NEDg | Description generation | batch_69a6738d22f48190b7933ffeb84e8b9c |
completed | March 3, 2026, 5:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a673dc2af88190896776ed418ffa44 |
completed | March 3, 2026, 5:38 a.m. |
Created at: March 1, 2026, 7:35 p.m.