Triple
T15884270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Todd |
E385149
|
entity |
| Predicate | placeOfDeath |
P21
|
FINISHED |
| Object | Frankfort, Kentucky |
E49744
|
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: Frankfort, Kentucky | Statement: [Thomas Todd, placeOfDeath, Frankfort, Kentucky]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frankfort, Kentucky Context triple: [Thomas Todd, placeOfDeath, Frankfort, Kentucky]
-
A.
Frankfort, Kentucky
chosen
Frankfort, Kentucky is the small but historically significant capital city of the U.S. state of Kentucky, located along the Kentucky River in the central part of the state.
-
B.
Frankfort
Frankfort is a suburban village in northeastern Illinois known for its historic downtown and residential communities within the Chicago metropolitan area.
-
C.
Frankfort
Frankfort is a small village located in Herkimer County in central New York State.
-
D.
Richmond, Kentucky
Richmond, Kentucky is a city in central Kentucky known as the home of Eastern Kentucky University and a regional center for education, commerce, and healthcare.
-
E.
Lexington, Kentucky
Lexington, Kentucky is a major city in the Bluegrass region renowned as the "Horse Capital of the World" for its thoroughbred breeding and racing industry.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156186b98819087b80ade6bd71a69 |
completed | April 16, 2026, 9:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb04598e0819094274868941195b9 |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:51 a.m.