Triple
T5310481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoffrey Faber |
E119013
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Geoffrey Faber |
E119013
|
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: Geoffrey Faber | Statement: [Geoffrey Faber, name, Geoffrey Faber]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geoffrey Faber Context triple: [Geoffrey Faber, name, Geoffrey Faber]
-
A.
Geoffrey Faber
chosen
Geoffrey Faber was a British publisher and poet best known as the co-founder of the influential London publishing house Faber and Faber.
-
B.
Harold Monro
Harold Monro was an influential early 20th-century British poet and literary figure best known for running the Poetry Bookshop in London and championing modern and Georgian poets.
-
C.
Edmund Goulding
Edmund Goulding was a British-born film director and screenwriter best known for helming sophisticated Hollywood dramas during the 1930s and 1940s.
-
D.
Stanley Lane-Poole
Stanley Lane-Poole was a British orientalist, archaeologist, and numismatist known for his influential works on Islamic history, art, and coinage.
-
E.
G. Albert Lansburgh
G. Albert Lansburgh was an American architect best known for his elegant theater and opera house designs in the early 20th century, particularly on the West Coast.
- 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_69bd446b57bc8190a513d2e6c40314f3 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd85343ae08190bd9801ea4eac7003 |
completed | March 20, 2026, 5:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf11033c448190ab64600913ee8a9c |
completed | March 21, 2026, 9:43 p.m. |
Created at: March 20, 2026, 1:53 p.m.