Triple
T20055086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Simon Ritchie |
E499306
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | John Ritchie |
—
|
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: John Ritchie | Statement: [John Simon Ritchie, father, John Ritchie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Ritchie Context triple: [John Simon Ritchie, father, John Ritchie]
-
A.
John Ritchie
chosen
John Ritchie was the father of John Simon Ritchie, better known as Sid Vicious of the Sex Pistols.
-
B.
Blair Gordon Newell
Blair Gordon Newell was the first husband of American actress Gloria Stuart, known primarily for his connection to her early life and career.
-
C.
Michael S. Paterson
Michael S. Paterson is a British computer scientist and mathematician known for his contributions to theoretical computer science and combinatorial game theory.
-
D.
Richard Hamlett
Richard Hamlett is an American real estate developer best known for his marriage to actress and singer Debbie Reynolds.
-
E.
John Harrold
John Harrold is a British illustrator best known for his long-running work on the Rupert Bear comic strips and annuals.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66332b300819097f5dca1636e5822 |
completed | April 20, 2026, 5:32 p.m. |
Created at: April 11, 2026, 3:38 p.m.