Triple
T28072228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nisa |
E709437
|
entity |
| Predicate | hasMunicipalRelationshipWith |
P178783
|
FINISHED |
| Object | Liberec |
—
|
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: Liberec | Statement: [Nisa, hasMunicipalRelationshipWith, Liberec]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMunicipalRelationshipWith Context triple: [Nisa, hasMunicipalRelationshipWith, Liberec]
-
A.
typeOfMunicipalRelationship
Indicates a formal type or category of administrative or cooperative relationship that exists between municipalities.
-
B.
isMunicipalHomeOf
Indicates that a municipality serves as the official home base or hosting location for a particular entity or organization.
-
C.
servesAsMunicipalAuthorityFor
Indicates that an entity functions as the official municipal governing or administrative authority for a specified locality or jurisdiction.
-
D.
hasMunicipalPart
Indicates that an administrative or territorial entity includes a municipality as one of its constituent parts.
-
E.
hasMunicipalityBoundaryRole
Indicates that an entity participates in or is assigned a specific role related to the boundary of a municipality (such as defining, managing, or being affected by that boundary).
- F. None of above. chosen
Provenance (4 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_69ef9b6f8078819098b741274cd1a2ee |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f71422adac8190a5ceb32dcf820833 |
completed | May 3, 2026, 9:23 a.m. |
| PD | Predicate disambiguation | batch_69f712764d2c819081b64b27e5de4a13 |
completed | May 3, 2026, 9:16 a.m. |
| PDg | Predicate description generation | batch_69f71421e8d08190807ccfb15d0f0ddb |
completed | May 3, 2026, 9:23 a.m. |
Created at: April 27, 2026, 8:46 p.m.