Triple
T20490642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richard Howe |
E502732
|
entity |
| Predicate | nobleTitle |
P914
|
FINISHED |
| Object | Baron Howe |
—
|
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: Baron Howe | Statement: [Richard Howe, nobleTitle, Baron Howe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Baron Howe Context triple: [Richard Howe, nobleTitle, Baron Howe]
-
A.
Baron Howe
chosen
Baron Howe is a British noble title historically associated with the distinguished naval commander Admiral Richard Howe.
-
B.
Arent Roggeveen
Arent Roggeveen was a 17th-century Dutch cartographer and explorer known for his work in mapping and describing distant lands and seas.
-
C.
Arent Roggeveen
Arent Roggeveen was a 17th-century Dutch cartographer and astronomer known for his work on navigation and mapping, particularly of the Atlantic and West African coasts.
-
D.
Gough
Gough is a surname of English origin borne by various notable individuals across fields such as acting, politics, and sports.
-
E.
Finsch
Finsch is the authority who first formally described the Fiordland crested penguin in the scientific literature.
- 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_69e0b4b0373881909dd3e9387f82eab4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69cb8e7848190a1dc497a10ae798c |
completed | April 20, 2026, 9:38 p.m. |
Created at: April 16, 2026, 11:35 a.m.