Triple
T7794522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Thomas |
E180264
|
entity |
| Predicate | coAuthorWith |
P398
|
FINISHED |
| Object | Andrew Hunt |
E180037
|
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: Andrew Hunt | Statement: [David Thomas, coAuthorWith, Andrew Hunt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Hunt Context triple: [David Thomas, coAuthorWith, Andrew Hunt]
-
A.
Andrew Hunt
chosen
Andrew Hunt is a prominent software developer and author best known for co-writing the influential book "The Pragmatic Programmer."
-
B.
Michael Feathers
Michael Feathers is a software engineer, consultant, and author known for his influential work on legacy code, refactoring, and improving software design and maintainability.
-
C.
Eric Evans
Eric Evans is a software engineer and thought leader best known for originating and popularizing the concept of Domain-Driven Design in enterprise software development.
-
D.
Alex Heineman
Alex Heineman is a film producer known for his work on the historical thriller "Operation Finale" and other feature films.
-
E.
Tim Herlihy
Tim Herlihy is an American screenwriter and producer best known for his long-running collaboration with Adam Sandler on numerous comedy films.
- 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_69ca827d22208190b4dc5aa680edcf5d |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cae93b262c8190b55e5ab2bc72d894 |
completed | March 30, 2026, 9:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb13ea96cc819081ac26db3ecf4481 |
completed | March 31, 2026, 12:23 a.m. |
Created at: March 30, 2026, 4:31 p.m.