Triple
T35978780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sylvan Township, Washtenaw County, Michigan |
E1040498
|
entity |
| Predicate | borderingOrNearbyCity |
P57276
|
FINISHED |
| Object | Chelsea, Michigan |
—
|
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: Chelsea, Michigan | Statement: [Sylvan Township, Washtenaw County, Michigan, borderingOrNearbyCity, Chelsea, Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderingOrNearbyCity Context triple: [Sylvan Township, Washtenaw County, Michigan, borderingOrNearbyCity, Chelsea, Michigan]
-
A.
isNeighboringCityOf
chosen
Indicates that one city is geographically adjacent to or directly borders another city.
-
B.
cityIsBorderCity
Indicates that a city is located on or near a boundary between two regions, countries, or administrative areas.
-
C.
hasNearbyCityArea
Indicates that one area is geographically close to or adjacent to a city area.
-
D.
hasNearbyCityFunction
Indicates that one entity serves as a nearby urban center or city-like service hub for another entity.
-
E.
hasBorderCity
Indicates that one location is a city situated on or very near the border of another geographic or political region.
- F. None of above.
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_69f76e27758c81909b711cf38a130aaf |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ffbf84f4948190b41a7bba07ae61ec |
completed | May 9, 2026, 11:13 p.m. |
| PD | Predicate disambiguation | batch_69ffbf0a59f88190870dbe25d8a63a00 |
completed | May 9, 2026, 11:11 p.m. |
Created at: May 3, 2026, 4:07 p.m.