Triple
T24375449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harrison Township, Michigan |
E614459
|
entity |
| Predicate | northeastOf |
P15148
|
FINISHED |
| Object | Detroit, 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: Detroit, Michigan | Statement: [Harrison Township, Michigan, northeastOf, Detroit, Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: northeastOf Context triple: [Harrison Township, Michigan, northeastOf, Detroit, Michigan]
-
A.
locatedNorthEastOf
chosen
Indicates that one entity is positioned to the north-east of another entity in space.
-
B.
locatedNorthOf
Indicates that one entity is positioned geographically to the north of another entity.
-
C.
liesNorthwestOf
Indicates that one entity is located to the northwest of another entity, combining both a more northern and more western position relative to it.
-
D.
locatedNorthwestOf
Indicates that one entity is positioned to the northwest of another entity in space or geography.
-
E.
liesSoutheastOf
Indicates that one entity is located to the southeast of another, combining both a southern and eastern directional relationship.
- 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_69e2d7e1e010819098b95eb3f905943d |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f293d73c0c8190b80e257845a04c57 |
completed | April 29, 2026, 11:27 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:02 a.m.