Triple
T31468942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Compostelan Holy Year |
E802799
|
entity |
| Predicate | HolyDoorLocation |
P12030
|
FINISHED |
| Object | Cathedral of Santiago de Compostela |
—
|
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: Cathedral of Santiago de Compostela | Statement: [Compostelan Holy Year, HolyDoorLocation, Cathedral of Santiago de Compostela]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: HolyDoorLocation Context triple: [Compostelan Holy Year, HolyDoorLocation, Cathedral of Santiago de Compostela]
-
A.
doorwayFeature
Indicates that one entity is a feature, characteristic, or structural element specifically associated with a doorway of another entity.
-
B.
doorLocation
chosen
Indicates the spatial position or placement of a door relative to a reference structure or area.
-
C.
hallLocatedNear
Indicates that a hall is situated close to another specified place or entity in physical space.
-
D.
hallLocatedAt
Indicates that a hall is situated at or within a specific location or address.
-
E.
houseOfTheTempleLocation
Indicates the geographical location where the House of the Temple is situated.
- 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_69f348c84c1c81908739f100ecf7394e |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a5f71b2c8190aade8a83f465be0c |
completed | May 3, 2026, 1:33 a.m. |
| PD | Predicate disambiguation | batch_69f69fe66df08190958558d63ee623d9 |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 9:25 p.m.