Triple
T18619869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steward |
E455118
|
entity |
| Predicate | hasVariantSpelling |
P457
|
FINISHED |
| Object | Stewart |
—
|
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: Stewart | Statement: [Steward, hasVariantSpelling, Stewart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stewart Context triple: [Steward, hasVariantSpelling, Stewart]
-
A.
Stewart
chosen
Stewart is a common Scottish-origin surname borne by numerous notable figures across politics, law, the arts, and entertainment.
-
B.
Stewart-Murray
Stewart-Murray is a Scottish noble family name associated with the Dukes of Atholl and the broader Clan Murray lineage.
-
C.
Daniel Stewart
Daniel Stewart was an American Revolutionary War officer and early Georgia politician and militia leader for whom Stewart County, Georgia, is named.
-
D.
Daniel Stewart
Daniel Stewart is a British actor known for his work in television and theatre and as the son of renowned actor Sir Patrick Stewart.
-
E.
Jason Stewart
Jason Stewart is a film editor known for his work on the comedy-drama movie "World's Greatest Dad."
- 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_69d8d38bbe7c8190bdec3138e7d413c9 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54f00889c8190931f8d3fbabd531b |
completed | April 19, 2026, 9:54 p.m. |
Created at: April 10, 2026, 11:46 a.m.