Triple
T21874045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FEFE |
E540083
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Andrew Green |
—
|
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: Andrew Green | Statement: [FEFE, writer, Andrew Green]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Green Context triple: [FEFE, writer, Andrew Green]
-
A.
Andrew Green
chosen
Andrew Green was a British paranormal investigator and author known for his extensive work on ghost hunting and psychical research.
-
B.
James Green
James Green was an architect known for designing the Stoodley Pike Monument in West Yorkshire, England.
-
C.
Martin Green
Martin Green is a renowned Australian engineer and solar energy researcher recognized as a leading pioneer in photovoltaic technology.
-
D.
Richard Green
Richard Green was an American boxing referee best known for officiating major heavyweight bouts, including the 1980 title fight between Larry Holmes and Muhammad Ali.
-
E.
Christopher Greenup
Christopher Greenup was an early American politician who served as the third governor of Kentucky in the early 19th century.
- 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_69e0c478f59081909d54302b57fc1ce3 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f338757c81908005bfedb52b03cc |
completed | April 28, 2026, 5:49 p.m. |
Created at: April 16, 2026, 7:01 p.m.