Triple
T13392119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Graham |
E319599
|
entity |
| Predicate | hasRelationshipWith |
P2830
|
FINISHED |
| Object | Charlie Graham |
E1036473
|
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: Charlie Graham | Statement: [Peter Graham, hasRelationshipWith, Charlie Graham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charlie Graham Context triple: [Peter Graham, hasRelationshipWith, Charlie Graham]
-
A.
Charlie Graham
chosen
Charlie Graham is a person known primarily as the sibling of Peter Graham.
-
B.
Charlie Graham
Charlie Graham is the child of Steve Graham.
-
C.
Charlie Graham
Charlie Graham is the troubled young daughter whose eerie behavior and tragic fate drive much of the psychological and supernatural horror in the film "Hereditary."
-
D.
Colin Buchanan
Colin Buchanan is an Anglican bishop and liturgical scholar who served as the Bishop of Woolwich in the Church of England.
-
E.
Fred Kilgour
Fred Kilgour was an American librarian and information scientist best known for pioneering online library cataloging and founding the OCLC cooperative.
- 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_69d806b886bc8190b676e7768b8e01c5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dba0d74e5881909828854bba7d9a87 |
completed | April 12, 2026, 1:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f73981816881908aac3ab6b1921904 |
completed | May 3, 2026, 12:03 p.m. |
Created at: April 9, 2026, 9:34 p.m.