Triple
T4730178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mansfield |
E104984
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Heiligenhaus |
E288041
|
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: Heiligenhaus | Statement: [Mansfield, hasTwinTown, Heiligenhaus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heiligenhaus Context triple: [Mansfield, hasTwinTown, Heiligenhaus]
-
A.
Heiligenhaus
chosen
Heiligenhaus is a small town in North Rhine-Westphalia, western Germany, known for its manufacturing industry and location between Düsseldorf and Essen.
-
B.
Culemborg
Culemborg is a historic town in the Dutch province of Gelderland, known for its medieval center and role in the early Dutch colonial era.
-
C.
Rolandswerth
Rolandswerth is a district of the German town of Remagen, situated along the Rhine River in the state of Rhineland-Palatinate.
-
D.
Sassenheim
Sassenheim is a town in the Dutch province of South Holland, known historically for its bulb-growing industry and location within the Duin- en Bollenstreek (Dune and Bulb Region).
-
E.
Zutphen
Zutphen is a historic city in the eastern Netherlands known for its well-preserved medieval center and location along the river IJssel.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd43ee52048190b81a4f066534ffb3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64629bc081908754aa8a2630091f |
completed | March 20, 2026, 3:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c673e0dbdc81909745d2a35bd53f88 |
completed | March 27, 2026, 12:11 p.m. |
Created at: March 20, 2026, 1:19 p.m.