Triple
T2084163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Partners In Health |
E45309
|
entity |
| Predicate | hasKeyPerson |
P256
|
FINISHED |
| Object |
Sheila Davis
Sheila Davis is a global health leader and nurse who serves as a key executive at the social justice–focused healthcare organization Partners In Health.
|
E265212
|
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: Sheila Davis | Statement: [Partners In Health, hasKeyPerson, Sheila Davis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sheila Davis Context triple: [Partners In Health, hasKeyPerson, Sheila Davis]
-
A.
Sharen Davis
Sharen Davis is an acclaimed American costume designer known for her work on major films such as "Dreamgirls," "Ray," and "The Pursuit of Happyness."
-
B.
Lyn Davis
Lyn Davis is best known as the wife of influential American television writer and producer Norman Lear.
-
C.
Nina Davis
Nina Davis is an American basketball player best known as a standout forward for the Baylor Lady Bears, where she earned multiple All-American honors and led the team to deep NCAA Tournament runs.
-
D.
Candy Clark
Candy Clark is an American actress best known for her Academy Award–nominated role in the coming-of-age film "American Graffiti."
-
E.
Kate Davis
Kate Davis was the wife of influential newspaper publisher and journalist Joseph Pulitzer.
- 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: Sheila Davis Triple: [Partners In Health, hasKeyPerson, Sheila Davis]
Generated description
Sheila Davis is a global health leader and nurse who serves as a key executive at the social justice–focused healthcare organization Partners In Health.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sheila Davis Target entity description: Sheila Davis is a global health leader and nurse who serves as a key executive at the social justice–focused healthcare organization Partners In Health.
-
A.
Sharen Davis
Sharen Davis is an acclaimed American costume designer known for her work on major films such as "Dreamgirls," "Ray," and "The Pursuit of Happyness."
-
B.
Lyn Davis
Lyn Davis is best known as the wife of influential American television writer and producer Norman Lear.
-
C.
Nina Davis
Nina Davis is an American basketball player best known as a standout forward for the Baylor Lady Bears, where she earned multiple All-American honors and led the team to deep NCAA Tournament runs.
-
D.
Candy Clark
Candy Clark is an American actress best known for her Academy Award–nominated role in the coming-of-age film "American Graffiti."
-
E.
Kate Davis
Kate Davis was the wife of influential newspaper publisher and journalist Joseph Pulitzer.
- 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_69a8891869c88190a02643e3bb746f59 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abba524b60819089a11957ce6dbc4b |
completed | March 7, 2026, 5:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aebf11478c8190988a280a5088b25d |
completed | March 9, 2026, 12:37 p.m. |
| NEDg | Description generation | batch_69aec3cf3d8881908d0e5d72f625634c |
completed | March 9, 2026, 12:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69aec488a4448190b2e9bf40a0fea5ee |
completed | March 9, 2026, 1 p.m. |
Created at: March 4, 2026, 7:41 p.m.