Triple
T19347871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carlisle Township |
E483930
|
entity |
| Predicate | subdivisionName |
P747
|
FINISHED |
| Object | Carlisle Township |
—
|
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: Carlisle Township | Statement: [Carlisle Township, subdivisionName, Carlisle Township]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carlisle Township Context triple: [Carlisle Township, subdivisionName, Carlisle Township]
-
A.
Carlisle Township
chosen
Carlisle Township is a civil township located within Lorain County in the state of Ohio, United States.
-
B.
Landis Township
Landis Township was a former municipality in Cumberland County, New Jersey, that was eventually incorporated into the city of Vineland.
-
C.
Collegeville Township
Collegeville Township is a local governmental subdivision that encompasses and administers the community of Collegeville and its surrounding area.
-
D.
Courtland Township
Courtland Township is a civil township located in Kent County in the U.S. state of Michigan.
-
E.
Hilliard Township
Hilliard Township is a small rural municipality located within Ontario’s Timiskaming District in Canada.
- 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_69d8e8d244f8819080eb1f3491300db2 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e6185c95248190b1e5bb8626489767 |
completed | April 20, 2026, 12:13 p.m. |
Created at: April 10, 2026, 1:34 p.m.