Triple
T503849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holabird & Roche |
E10457
|
entity |
| Predicate | hasPartner |
P1136
|
FINISHED |
| Object | Martin Roche |
E78953
|
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: Martin Roche | Statement: [Holabird & Roche, hasPartner, Martin Roche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martin Roche Context triple: [Holabird & Roche, hasPartner, Martin Roche]
-
A.
Martin Roche
chosen
Martin Roche was an American architect best known as a partner in the influential Chicago firm Holabird & Roche, which helped shape the city’s early skyscraper architecture.
-
B.
Roger Wehrli
Roger Wehrli is a Hall of Fame American football cornerback best known for his standout career with the St. Louis Cardinals in the NFL during the 1970s.
-
C.
Eric Thibault
Eric Thibault is a professional basketball coach best known for leading the WNBA’s Washington Mystics.
-
D.
Sébastien Jodogne
Sébastien Jodogne is a free software developer best known for creating the open-source medical imaging platform Orthanc and for his significant contributions to open healthcare technologies.
-
E.
Anthony Barra
Anthony Barra is the husband of Mary Barra, the high-profile CEO of General Motors.
- 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_69a2e848adf881908e5e04f7af030093 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f1357738819085eae6c10fa2fca9 |
completed | Feb. 28, 2026, 1:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a56c475ce88190bf16e5ee76f1d3b5 |
completed | March 2, 2026, 10:53 a.m. |
Created at: Feb. 28, 2026, 1:12 p.m.