Triple
T10265814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Norman |
E240707
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Jan Norman |
E851826
|
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: Jan Norman | Statement: [Peter Norman, relative, Jan Norman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jan Norman Context triple: [Peter Norman, relative, Jan Norman]
-
A.
Jan Norman
chosen
Jan Norman is known as the wife of Australian Olympic sprinter Peter Norman, who famously protested racial discrimination at the 1968 Mexico City Games.
-
B.
Leo Sayer
Leo Sayer is an English pop singer-songwriter best known for his 1970s hits such as "You Make Me Feel Like Dancing" and "When I Need You."
-
C.
Stevie Crawford
Stevie Crawford is a Scottish former professional footballer and coach best known as a prolific forward in the Scottish leagues and later as a manager.
-
D.
Paul Young
Paul Young is an American politician serving as the mayor of Memphis, Tennessee.
-
E.
Paul Young
Paul Young is an English pop and soul singer best known for his 1980s hits such as "Everytime You Go Away" and "Come Back and Stay."
- 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_69d381a94c1881908fc38fc263d9b9c2 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d25f17ec8190ac57836d36cb39db |
completed | April 7, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71ce5ac10819092c287bc435ae010 |
completed | April 9, 2026, 3:28 a.m. |
Created at: April 6, 2026, 11:33 a.m.