Triple
T31519491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sydlangeland Municipality |
E804165
|
entity |
| Predicate | locatedInPre2007County |
P110432
|
FINISHED |
| Object | Funen County |
E1750840
|
NE 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: Funen County | Statement: [Sydlangeland Municipality, locatedInPre2007County, Funen County]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInPre2007County Context triple: [Sydlangeland Municipality, locatedInPre2007County, Funen County]
-
A.
locatedInCountySeatOfCounty
Indicates that one entity is located in the county seat city or town of the specified county.
-
B.
hasFormerCounty
chosen
Indicates that an entity was previously part of, or administered by, a particular county in the past but no longer is.
-
C.
isInCountySeatOf
Indicates that one entity is located within the town or city that serves as the administrative center (county seat) of a specified county.
-
D.
hasCountySeatOfParentCounty
Indicates that a location serves as the county seat (administrative center) for the county that is the parent of another referenced entity.
-
E.
previousCounty
Indicates that one county was the immediately preceding county associated with an entity before the current or later county.
- F. None of above.
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_69f348cf839c81908657048402f7f97b |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a01a48fbbd481908ccf75551dcf4647 |
completed | May 11, 2026, 9:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2b79bd1b208190a8b7a8af0f421615 |
completed | June 12, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_6a01a2d6db208190b11c1af601a544f5 |
completed | May 11, 2026, 9:35 a.m. |
Created at: April 30, 2026, 9:55 p.m.