Triple
T7990747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Ward |
E185998
|
entity |
| Predicate | coAuthorWith |
P398
|
FINISHED |
| Object | Donald Brownlee |
E161126
|
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: Donald Brownlee | Statement: [Peter Ward, coAuthorWith, Donald Brownlee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donald Brownlee Context triple: [Peter Ward, coAuthorWith, Donald Brownlee]
-
A.
Donald Brownlee
chosen
Donald Brownlee is an American astronomer and astrobiologist best known for co-developing the Rare Earth hypothesis and leading NASA’s Stardust mission to collect samples from a comet.
-
B.
Brian Gilbert
Brian Gilbert is a British film and television director known for works such as the biographical drama "Tom & Viv."
-
C.
Timothy “Tee” Brown
Timothy “Tee” Brown is a music producer best known for his work on the Kanye West track “Use This Gospel.”
-
D.
Dan Beeman
Dan Beeman is a member of the band Helmet, contributing to the influential American alternative metal group's lineup.
-
E.
Lyle Campbell
Lyle Campbell is an American linguist renowned for his work in historical linguistics and the documentation and classification of indigenous languages of the Americas.
- 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_69ca829c6c308190ab05b43d234c52b2 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c6fc19c8190b98023e257c2f4f2 |
completed | March 31, 2026, 3:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe0f5c22881908044a178d670684c |
completed | March 31, 2026, 2:57 p.m. |
Created at: March 30, 2026, 5:16 p.m.