Triple
T17014121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nation |
E412773
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Carrie Nation |
E367631
|
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: Carrie Nation | Statement: [Nation, hasNotableBearer, Carrie Nation]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carrie Nation Context triple: [Nation, hasNotableBearer, Carrie Nation]
-
A.
Carry Nation
chosen
Carry Nation was a radical American temperance activist best known for smashing saloons with a hatchet in the early 20th century.
-
B.
Lucy Barker
Lucy Barker is the main character portrayed by Lucille Ball in the 1986 American sitcom "Life with Lucy."
-
C.
Lucy Barker
Lucy Barker is a person known primarily through her familial connection to Kevin McGibbon.
-
D.
Lucy Barker
Lucy Barker is a character in the musical "Sweeney Todd," known as the tragic wife of Benjamin Barker and mother of Johanna.
-
E.
Ida Red
"Ida Red" is a traditional American folk and fiddle tune that influenced early rock and roll, notably inspiring Chuck Berry's hit "Maybellene."
- 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d47e64f081908f43870c7564d0ae |
completed | April 18, 2026, 6:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b4990948190861ff81f8fc3e8f2 |
completed | May 10, 2026, 11:56 p.m. |
Created at: April 10, 2026, 5:33 a.m.