Triple
T14077620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gordon Harker |
E338778
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Harker |
E338778
|
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: Harker | Statement: [Gordon Harker, familyName, Harker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harker Context triple: [Gordon Harker, familyName, Harker]
-
A.
Harker
chosen
Harker is a surname of English origin borne by various notable individuals, including actors, writers, and public figures.
-
B.
Nightcliff
Nightcliff is a coastal suburb of Darwin in Australia's Northern Territory, known for its scenic foreshore, jetty, and relaxed residential atmosphere.
-
C.
Hazlemere
Hazlemere is a suburban village and civil parish in Buckinghamshire, England, situated near High Wycombe.
-
D.
Harkness
Harkness is a surname of Scottish origin borne by various notable individuals in fields such as business, philanthropy, and the arts.
-
E.
Schuylar
Schuylar is a given name that functions as a spelling variant of the name Schuyler.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5cdd288190914e1d57321b3554 |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb670f51c819088e8d0137f8d3bb1 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:21 p.m.