Triple
T18936082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bergkirche |
E463249
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Calvary hill |
—
|
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: Calvary hill | Statement: [Bergkirche, hasPart, Calvary hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Calvary hill Context triple: [Bergkirche, hasPart, Calvary hill]
-
A.
Calvary Hill
Calvary Hill is a notable religious and historical site in the Slovak city of Nitra, known for its chapels and scenic views over the surrounding area.
-
B.
Calvary Hill
Calvary Hill is a notable religious and scenic hilltop site in Sátoraljaújhely, Hungary, known for its chapels and panoramic views of the surrounding area.
-
C.
Calvary
Calvary is a small unincorporated community in Grady County, Georgia, known for its rural character and annual Mule Day festival.
-
D.
Calvary
Calvary is a 2014 Irish black comedy-drama film about a good priest facing a death threat from a troubled parishioner, noted for its dark humor and moral complexity.
-
E.
Calvary
chosen
Calvary is the hill outside Jerusalem traditionally identified as the site where Jesus Christ was crucified.
- 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d3e7b87c81909dc29defb33c8e00 |
completed | April 20, 2026, 7:21 a.m. |
Created at: April 10, 2026, 11:59 a.m.