Triple
T15002068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horses of Saint Mark |
E374114
|
entity |
| Predicate | formerDisplayLocation |
P55436
|
FINISHED |
| Object | façade of St. Mark's Basilica |
—
|
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: façade of St. Mark's Basilica | Statement: [Horses of Saint Mark, formerDisplayLocation, façade of St. Mark's Basilica]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerDisplayLocation Context triple: [Horses of Saint Mark, formerDisplayLocation, façade of St. Mark's Basilica]
-
A.
formerlyKnownLocationAs
Indicates that an entity was previously known or referred to by a different location name or designation.
-
B.
formerlyLocatedOn
chosen
Indicates that an entity was once located on or situated upon another entity, but is no longer in that position.
-
C.
locatedAtFormer
Indicates that an entity is currently located at a place where another entity was previously located.
-
D.
formerSiteOf
Indicates that a location previously hosted or contained something (such as a structure, organization, or event) that is no longer present there.
-
E.
previousLocationName
Indicates that one entity specifies the name of a location where another entity was situated or occurred before its current location.
- 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_69d85ccc84388190aa151e5173370c8d |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded72fec948190b1c9705538c57976 |
completed | April 15, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69de9a6531a88190acde65199a477350 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:54 a.m.