Triple
T970738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edward Albee |
E20937
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Jonathan Thomas
Jonathan Thomas is best known as the longtime husband of acclaimed American playwright Edward Albee.
|
E161289
|
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: Jonathan Thomas | Statement: [Edward Albee, spouse, Jonathan Thomas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jonathan Thomas Context triple: [Edward Albee, spouse, Jonathan Thomas]
-
A.
R. L. Thornton
R. L. Thornton was a prominent mid-20th-century Dallas businessman and civic leader who played a key role in the city’s economic growth and urban development.
-
B.
Dan Jewett
Dan Jewett is an American science teacher known for his brief marriage to billionaire philanthropist and novelist MacKenzie Scott.
-
C.
Joe Ellis
Joe Ellis is an American sports executive best known as the longtime president and CEO of the Denver Broncos in the National Football League.
-
D.
Ed Oates
Ed Oates is an American engineer and entrepreneur best known as one of the co-founders of Oracle Corporation, a pioneering company in relational database technology.
-
E.
Lee Holdridge
Lee Holdridge is an American composer and orchestrator best known for his work on film and television scores, including numerous collaborations with John Denver.
- 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: Jonathan Thomas Triple: [Edward Albee, spouse, Jonathan Thomas]
Generated description
Jonathan Thomas is best known as the longtime husband of acclaimed American playwright Edward Albee.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jonathan Thomas Target entity description: Jonathan Thomas is best known as the longtime husband of acclaimed American playwright Edward Albee.
-
A.
R. L. Thornton
R. L. Thornton was a prominent mid-20th-century Dallas businessman and civic leader who played a key role in the city’s economic growth and urban development.
-
B.
Dan Jewett
Dan Jewett is an American science teacher known for his brief marriage to billionaire philanthropist and novelist MacKenzie Scott.
-
C.
Joe Ellis
Joe Ellis is an American sports executive best known as the longtime president and CEO of the Denver Broncos in the National Football League.
-
D.
Ed Oates
Ed Oates is an American engineer and entrepreneur best known as one of the co-founders of Oracle Corporation, a pioneering company in relational database technology.
-
E.
Lee Holdridge
Lee Holdridge is an American composer and orchestrator best known for his work on film and television scores, including numerous collaborations with John Denver.
- 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_69a493b33d2c81909c52c369d3ca8436 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b44aa6088190a90c44a8f694ec41 |
completed | March 1, 2026, 9:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ace540122c8190824f6de78dc1a411 |
completed | March 8, 2026, 2:56 a.m. |
| NEDg | Description generation | batch_69ace62a94e88190883d25cdb748e8c1 |
completed | March 8, 2026, 2:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ace68ab3788190bc3b55dd9a0fe267 |
completed | March 8, 2026, 3:01 a.m. |
Created at: March 1, 2026, 7:40 p.m.