Triple
T37586903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M-31 |
E935141
|
entity |
| Predicate | formerRouteNumberReusedAs |
P22310
|
FINISHED |
| Object | US Highway 31 in 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: US Highway 31 in Michigan | Statement: [M-31, formerRouteNumberReusedAs, US Highway 31 in Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerRouteNumberReusedAs Context triple: [M-31, formerRouteNumberReusedAs, US Highway 31 in Michigan]
-
A.
formerRouteNumber
chosen
Indicates that an entity previously had a specific route number before being renumbered, discontinued, or otherwise changed.
-
B.
formerRouteType
Indicates that an entity previously had a specific route classification or type, which is no longer its current status.
-
C.
usesFormerRouteOf
Indicates that one route, service, or pathway currently follows all or part of the alignment or path that was previously used by another route.
-
D.
stateRouteNumberOverlap
Indicates that two or more state-designated routes share the same physical roadway segment for part of their length.
-
E.
formerMainRouteBetween
Indicates that a route once served as the primary connection between two locations but no longer holds that status.
- 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_69f76ece61dc8190a0ab33f8d87d0a7e |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00d9717a9881908194163d719f14d6 |
completed | May 10, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a00d91db2ec81909ebacfc9f0d11dd8 |
completed | May 10, 2026, 7:14 p.m. |
Created at: May 3, 2026, 4:17 p.m.