Triple
T6270798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | McMillan |
E140527
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | David McMillan |
E469267
|
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: David McMillan | Statement: [McMillan, hasNotableBearer, David McMillan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David McMillan Context triple: [McMillan, hasNotableBearer, David McMillan]
-
A.
David McMillan
chosen
David McMillan is the son of Nobel Prize–winning American physicist Edwin McMillan.
-
B.
Robert McMillan
Robert McMillan was a historical figure known as the original owner of the ship Balclutha, a notable sailing vessel from the late 19th century.
-
C.
Doug McMillan
Doug McMillan is an American business executive best known as the president and chief executive officer of Walmart Inc.
-
D.
Michael McKinnell
Michael McKinnell was a British-born American architect best known as the co-designer of Boston City Hall and a leading figure in late-20th-century civic architecture.
-
E.
Andrew McMillan
Andrew McMillan is a software developer and open-source contributor known for his work on email and groupware technologies, particularly with the Kolab groupware server.
- 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_69c008cabc4081909723e2547c9d6cc0 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063bb340c8190ab81b249cefa91ca |
completed | March 22, 2026, 9:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c67c3b6cdc8190ad9e10957e301a57 |
completed | March 27, 2026, 12:46 p.m. |
Created at: March 22, 2026, 4:25 p.m.