Triple
T19528017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bielefeld viaduct |
E488581
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Brackwede |
—
|
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: Brackwede | Statement: [Bielefeld viaduct, locatedNear, Brackwede]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brackwede Context triple: [Bielefeld viaduct, locatedNear, Brackwede]
-
A.
Brackwede
chosen
Brackwede is a district of the city of Bielefeld in North Rhine-Westphalia, Germany, known historically as an independent town before its incorporation.
-
B.
Farnhill
Farnhill is a small village in North Yorkshire, England, situated on the hillside above the River Aire in the Aire Valley.
-
C.
Bracebridge Heath
Bracebridge Heath is a large village and civil parish in Lincolnshire, England, situated just south of the city of Lincoln.
-
D.
Wickhambrook
Wickhambrook is a rural village and civil parish in the county of Suffolk in eastern England.
-
E.
Buckthorne
Buckthorne is the fictional protagonist of the satirical work "Buckthorne and His Friends," around whom the story’s social observations and character interactions revolve.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6363d43148190af25caaa57accf9b |
completed | April 20, 2026, 2:20 p.m. |
Created at: April 10, 2026, 1:41 p.m.