Triple
T5966153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dan Flavin |
E132756
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Tracy Harris
Tracy Harris is an American artist known for her abstract and minimalist paintings and for her marriage to light artist Dan Flavin.
|
E674224
|
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: Tracy Harris | Statement: [Dan Flavin, spouse, Tracy Harris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tracy Harris Context triple: [Dan Flavin, spouse, Tracy Harris]
-
A.
Tracie Simpson
Tracie Simpson is a British television producer best known for her work on the long-running science fiction series Doctor Who.
-
B.
Tracy Stevens
Tracy Stevens is best known as the wife of American basketball coach and executive Brad Stevens.
-
C.
Tracy Stevens
Tracy Stevens is a central astronaut character in the alternate-history space drama series "For All Mankind," known for her pioneering role in NASA’s evolving lunar and space missions.
-
D.
Tracy Benchley
Tracy Benchley is a child of American author and screenwriter Peter Benchley, best known for writing the novel "Jaws."
-
E.
Tricia Miller
Tricia Miller is a troubled but endearing young inmate in the television series "Orange Is the New Black," known for her close bond with fellow prisoner Poussey Washington.
- 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: Tracy Harris Triple: [Dan Flavin, spouse, Tracy Harris]
Generated description
Tracy Harris is an American artist known for her abstract and minimalist paintings and for her marriage to light artist Dan Flavin.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tracy Harris Target entity description: Tracy Harris is an American artist known for her abstract and minimalist paintings and for her marriage to light artist Dan Flavin.
-
A.
Tracie Simpson
Tracie Simpson is a British television producer best known for her work on the long-running science fiction series Doctor Who.
-
B.
Tracy Stevens
Tracy Stevens is best known as the wife of American basketball coach and executive Brad Stevens.
-
C.
Tracy Stevens
Tracy Stevens is a central astronaut character in the alternate-history space drama series "For All Mankind," known for her pioneering role in NASA’s evolving lunar and space missions.
-
D.
Tracy Benchley
Tracy Benchley is a child of American author and screenwriter Peter Benchley, best known for writing the novel "Jaws."
-
E.
Tricia Miller
Tricia Miller is a troubled but endearing young inmate in the television series "Orange Is the New Black," known for her close bond with fellow prisoner Poussey Washington.
- 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_69c0086c2364819091e9fe2f58fa2517 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c03a3e06848190b1d1a191db257a07 |
completed | March 22, 2026, 6:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c86117b56881909168f39747504797 |
completed | March 28, 2026, 11:15 p.m. |
| NEDg | Description generation | batch_69c861c305c08190a09589d840aba410 |
completed | March 28, 2026, 11:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8627e9a6c8190baf4e8bb113845f1 |
completed | March 28, 2026, 11:21 p.m. |
Created at: March 22, 2026, 4:03 p.m.