Triple
T6553212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Stevenson |
E152377
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | David Stevenson |
E471096
|
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: David Stevenson | Statement: [Robert Stevenson, child, David Stevenson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Stevenson Context triple: [Robert Stevenson, child, David Stevenson]
-
A.
David Stevenson
chosen
David Stevenson was a Scottish lighthouse engineer and member of the famous Stevenson family of civil engineers.
-
B.
Tim Stevenson
Tim Stevenson is a British public servant who has served as the ceremonial representative of the monarch in Oxfordshire.
-
C.
Dani Stevenson
Dani Stevenson is an American R&B singer best known for her early-2000s work, including featured and background vocals on popular hip-hop and R&B tracks.
-
D.
Roger Stevens
Roger Stevens was a prominent British civil servant and diplomat who notably served as the first Vice-Chancellor of the University of Leeds.
-
E.
Andrew Stewart
Andrew Stewart is an American lawyer and publisher best known as the former husband of lifestyle entrepreneur Martha Stewart.
- 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_69c688058d6881908c19b309cc55dbfa |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ae0847d88190b38f9d7dba0faae1 |
completed | March 27, 2026, 4:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6d55707d081908104f08e1d59d603 |
completed | March 27, 2026, 7:07 p.m. |
Created at: March 27, 2026, 1:51 p.m.