Triple
T15811327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andy Dwyer |
E383359
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Pawnee, Indiana |
E634122
|
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: Pawnee, Indiana | Statement: [Andy Dwyer, residence, Pawnee, Indiana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pawnee, Indiana Context triple: [Andy Dwyer, residence, Pawnee, Indiana]
-
A.
Pawnee, Indiana
chosen
Pawnee, Indiana is the fictional Midwestern town that serves as the primary setting for the television comedy series "Parks and Recreation."
-
B.
Pendleton, Indiana
Pendleton, Indiana is a small town in Madison County known for its historic downtown, Falls Park, and role as a gateway community between Indianapolis and east-central Indiana.
-
C.
La Paz, Indiana
La Paz, Indiana is a small Midwestern town located in northern Indiana within Marshall County.
-
D.
Osceola, Indiana
Osceola, Indiana is a small town in northern Indiana situated between the cities of South Bend and Elkhart.
-
E.
Brownsville, Indiana
Brownsville, Indiana is a small unincorporated community located in rural Union County in the eastern part of the state.
- 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_69d86da2858c819090cc8481e7207b6e |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0b52bbb888190b226567e84ced7e9 |
completed | April 16, 2026, 10:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002d966ffc8190aa0d9d3abf8ad593 |
completed | May 10, 2026, 7:02 a.m. |
Created at: April 10, 2026, 4:49 a.m.