Triple
T1006137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graham Hancock |
E21716
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Graham |
E75501
|
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: Graham | Statement: [Graham Hancock, givenName, Graham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Graham Context triple: [Graham Hancock, givenName, Graham]
-
A.
Graham
Graham is the surname of Elizabeth Arden, the pioneering Canadian-American businesswoman who founded the iconic Elizabeth Arden cosmetics empire.
-
B.
Graham
chosen
Graham is a masculine given name of English origin, historically derived from a surname and commonly used in English-speaking countries.
-
C.
Gordon
Gordon is the middle name of the famed Romantic poet Lord Byron, whose full name is George Gordon Byron.
-
D.
Snodgrass
Snodgrass is a surname of English and Scottish origin borne by various notable individuals in sports, politics, and the arts.
-
E.
Willard
Willard is a masculine given name of Old English origin meaning "resolute" or "strong-willed."
- 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_69a493c53e648190ae8cb76c433fd9a7 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b51434f081909b301ad1c151af03 |
completed | March 1, 2026, 9:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac537f6bb08190a94eb40bcc821224 |
completed | March 7, 2026, 4:34 p.m. |
Created at: March 1, 2026, 7:41 p.m.