Triple
T17865747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katherine Emery |
E446694
|
entity |
| Predicate | hasFamilyName |
P18
|
FINISHED |
| Object | Emery |
—
|
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: Emery | Statement: [Katherine Emery, hasFamilyName, Emery]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emery Context triple: [Katherine Emery, hasFamilyName, Emery]
-
A.
Emery
chosen
Emery is a surname of English origin borne by various notable individuals, including Sarah Jane Emery.
-
B.
Kimsey
Kimsey is a surname most notably associated with Jim Kimsey, the co-founder and first CEO of America Online (AOL).
-
C.
Larue
Larue is a Vietnamese beer brand produced by Asia Pacific Breweries, known for its pale lager popular in central Vietnam.
-
D.
Merritt
Merritt is a small city in south-central British Columbia, Canada, known as a ranching hub and gateway to the Nicola Valley.
-
E.
Merritt
Merritt is the first name of American actress Merritt Wever, known for her roles in television series such as "Nurse Jackie" and "Godless."
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49793a2588190bb341ac606d767fe |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 10, 2026, 10:17 a.m.