Triple
T5425305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Thurston |
E121348
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Thurston |
E299698
|
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: Thurston | Statement: [William Thurston, familyName, Thurston]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thurston Context triple: [William Thurston, familyName, Thurston]
-
A.
Thurston
chosen
Thurston is a village and civil parish in Suffolk, England, known for its rural character and local community amenities.
-
B.
Douglas
Douglas is a small lakeside city in Allegan County, Michigan, known for its arts community and proximity to Lake Michigan beaches.
-
C.
Douglas
Douglas is a small community located on Douglas Island across from downtown Juneau in southeastern Alaska.
-
D.
Douglas
Douglas is a suburban area of Cork, Ireland, known as a residential and commercial hub just southeast of Cork city centre.
-
E.
Douglas
Douglas is a narrow-gauge steam locomotive that operates on the historic Talyllyn Railway in Wales.
- 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_69bd463b58d88190b258261573de9e91 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd881598448190a9bb456dee36004b |
completed | March 20, 2026, 5:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf3abbd1e481909ffb443812a9485a |
completed | March 22, 2026, 12:41 a.m. |
Created at: March 20, 2026, 2:06 p.m.