Triple
T7737019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Esztergom |
E175407
|
entity |
| Predicate | basilicaIs |
P52073
|
FINISHED |
| Object | largest church in Hungary |
—
|
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: largest church in Hungary | Statement: [Esztergom, basilicaIs, largest church in Hungary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basilicaIs Context triple: [Esztergom, basilicaIs, largest church in Hungary]
-
A.
basilicaStyle
Indicates that something is designed, built, or characterized in the architectural style of a basilica.
-
B.
hasBasilica
Indicates that one entity possesses, contains, or is associated with a basilica as a significant feature or component.
-
C.
majorBasilicaOf
Indicates that one entity is designated as a major basilica associated with, located in, or belonging to another entity (typically a city, region, or religious jurisdiction).
-
D.
basilicaStatus
chosen
Indicates that an entity holds the official ecclesiastical designation or rank of a basilica within a religious tradition.
-
E.
otherMajorBasilica
Indicates that one basilica stands in a specified relationship as an “other” major basilica to another, distinguishing it from a primary or reference major basilica.
- 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_69c6995f9c60819092e386192bd63c6f |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c70402169481909b219dc5f4a64b9b |
completed | March 27, 2026, 10:26 p.m. |
| PD | Predicate disambiguation | batch_69c7016c4a748190a7012030edaefcee |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:07 p.m.