Triple
T28762981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | STH 23 |
E726167
|
entity |
| Predicate | connectsMajorCommunitiesIn |
P83783
|
FINISHED |
| Object | Wisconsin |
—
|
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: Wisconsin | Statement: [STH 23, connectsMajorCommunitiesIn, Wisconsin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsMajorCommunitiesIn Context triple: [STH 23, connectsMajorCommunitiesIn, Wisconsin]
-
A.
connectsCommunities
Indicates a relationship in which something links or brings together separate communities, enabling interaction, communication, or shared activity between them.
-
B.
connectsCommunity
Indicates a relationship where an entity links or brings together members or groups within a community, fostering interaction or cohesion among them.
-
C.
connectsInlandCommunitiesTo
Indicates a relationship in which something serves as a link or conduit between inland communities and another place, system, or network.
-
D.
connectsMunicipalities
chosen
Indicates a relationship where one entity serves as a link or route that joins two or more municipalities.
-
E.
connectsNeighborhoodsIn
Indicates a relationship where something (such as a route, road, or service) links or provides direct access between two or more neighborhoods.
- 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_69f03198be14819098fa74e48b3749bf |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69fd5d48855c8190bd93070b6a00d8b5 |
completed | May 8, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69fd5c9aabb88190912800d90184a89d |
completed | May 8, 2026, 3:46 a.m. |
Created at: April 28, 2026, 6:12 a.m.