Triple
T22225114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvey brothers |
E549316
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Robert Harvey |
—
|
NE NERFINISHED |
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: Robert Harvey | Statement: [Harvey brothers, hasPart, Robert Harvey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Harvey Context triple: [Harvey brothers, hasPart, Robert Harvey]
-
A.
Robert Harvey
chosen
Robert Harvey was a 19th-century distiller and entrepreneur best known for establishing the Bruichladdich whisky distillery on the Scottish island of Islay.
-
B.
Robert Harvey
Robert Harvey was an American publisher best known for creating and leading Harvey Comics, the company behind characters like Casper the Friendly Ghost and Richie Rich.
-
C.
Edward Reeves
Edward Reeves was a teacher and mentor known for instructing Lionel Logue, the Australian speech therapist famous for treating King George VI.
-
D.
Robert Harper
Robert Harper is a prominent computer scientist known for his foundational work in programming language theory and type systems, particularly in connection with the development of Standard ML.
-
E.
Robert Harper
Robert Harper was an American character actor known for his work in film and television, particularly in 1980s and 1990s dramas and comedies.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e403d6481909a94d0aaf157f6ef |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b93e2208190aee70ffd82962ea0 |
completed | April 28, 2026, 9:50 p.m. |
Created at: April 16, 2026, 8:37 p.m.