Triple
T36127879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Untertürkheim |
E1044931
|
entity |
| Predicate | municipalityCodeType |
P116809
|
FINISHED |
| Object | Gemeindeschlüssel von Stuttgart |
—
|
LITERAL FINISHED |
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: Gemeindeschlüssel von Stuttgart | Statement: [Untertürkheim, municipalityCodeType, Gemeindeschlüssel von Stuttgart]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: municipalityCodeType Context triple: [Untertürkheim, municipalityCodeType, Gemeindeschlüssel von Stuttgart]
-
A.
municipalCodeSystem
chosen
Indicates a system that defines, organizes, or standardizes codes or regulations used by a municipality.
-
B.
hasMunicipalityCode
Indicates that an entity is associated with a specific official municipality code used for administrative or identification purposes.
-
C.
hasMunicipalCodeCountry
Indicates that a municipal code is associated with, or belongs to, a specific country.
-
D.
municipalKey
Indicates a unique identifier that links an entity to a specific municipality within an administrative or geographic system.
-
E.
hasLocalGovernmentCode
Indicates that an entity is associated with a specific code assigned by a local government authority for identification or administrative purposes.
- 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_69f76e356c908190abc6ca1e6a05b011 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b3e2f3c08190be4fd1ae4fa1266d |
completed | May 3, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bcc47081909fe7d592ac69006c |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:08 p.m.