Triple
T29966500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cathedral of Isernia |
E761195
|
entity |
| Predicate | builtOnEarlierStructure |
P159860
|
FINISHED |
| Object | ancient Italic temple |
—
|
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: ancient Italic temple | Statement: [Cathedral of Isernia, builtOnEarlierStructure, ancient Italic temple]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: builtOnEarlierStructure Context triple: [Cathedral of Isernia, builtOnEarlierStructure, ancient Italic temple]
-
A.
builtOn
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
B.
builtStructureFor
Indicates that one entity constructed or assembled a structure specifically intended for the use, benefit, or purpose of another entity.
-
C.
hasEarlierStructureOnSite
chosen
Indicates that a given site previously contained an earlier structure before the current one.
-
D.
laterBuiltOverBy
Indicates that a structure or feature was constructed at a later time on top of, or replacing, an earlier one.
-
E.
hasFormerBuilding
Indicates that an entity previously occupied or used a different building, which is identified as its former building.
- 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_69f22466327481908ba6db916837bece |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6786a5c70819085a5d00be58d67cb |
completed | May 2, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69f673c4abec8190bc2379e66f4af0a9 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 6:30 p.m.