Triple
T9621821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cange |
E232359
|
entity |
| Predicate | associatedWithPerson |
P37
|
FINISHED |
| Object | Paul Farmer |
E7581
|
NE FINISHED |
How this triple was built (2 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 Farmer | Statement: [Cange, associatedWithPerson, Paul Farmer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Farmer Context triple: [Cange, associatedWithPerson, Paul Farmer]
-
A.
Paul Farmer
chosen
Paul Farmer was an American physician and anthropologist renowned for co-founding Partners In Health and pioneering community-based global health care for the poor.
-
B.
William H. Foege
William H. Foege is an American epidemiologist and former CDC director renowned for his pivotal role in developing the global strategy that led to the eradication of smallpox.
-
C.
Peter Piot
Peter Piot is a Belgian microbiologist and global health leader best known as a co-discoverer of the Ebola virus and a pioneering figure in HIV/AIDS research and policy.
-
D.
Theodore Redfield
Theodore Redfield is the son of Irene Redfield, a central character in Nella Larsen’s novel "Passing."
-
E.
Karl Gajdusek
Karl Gajdusek is an American screenwriter, producer, and showrunner known for his work on films such as "The King’s Man" and the TV series "Last Resort."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca84867bb88190b4b57dd5a56d5691 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9ad505588190b8c81ce09f1904ec |
completed | April 1, 2026, 10:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1797386d88190bc1d9309ecc1b4fb |
completed | April 4, 2026, 8:49 p.m. |
Created at: March 30, 2026, 8:10 p.m.