Triple
T4549759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mindelheim |
E110132
|
entity |
| Predicate | castleLocation |
P54730
|
FINISHED |
| Object | hill above the town |
—
|
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: hill above the town | Statement: [Mindelheim, castleLocation, hill above the town]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: castleLocation Context triple: [Mindelheim, castleLocation, hill above the town]
-
A.
castleLocatedIn
Indicates that a castle is situated within or belongs to a specific geographic or administrative location.
-
B.
castleBuilt
Indicates that a castle has been constructed or established, typically by a specific agent or during a particular time period.
-
C.
castlePosition
chosen
Indicates the spatial location or placement of a castle relative to a reference point or area.
-
D.
castleOverlooks
Indicates that a castle is positioned so that it has a clear, elevated view over a particular area, object, or landscape.
-
E.
castleBuiltFor
Indicates that a castle was constructed specifically for the benefit, use, or commission of a particular person, group, or purpose.
- 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_69bd4412524c8190be5bcc9ddee91848 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd57f3f8348190868e274ac4df87ce |
completed | March 20, 2026, 2:21 p.m. |
| PD | Predicate disambiguation | batch_69bd5223423c81908317351b58cff5f5 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:05 p.m.