Triple
T12959498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tours Cathedral |
E310100
|
entity |
| Predicate | followsBuildingOnSite |
P11081
|
FINISHED |
| Object | earlier Romanesque cathedral |
—
|
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: earlier Romanesque cathedral | Statement: [Tours Cathedral, followsBuildingOnSite, earlier Romanesque cathedral]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsBuildingOnSite Context triple: [Tours Cathedral, followsBuildingOnSite, earlier Romanesque cathedral]
-
A.
followsBuildingCode
Indicates that one entity complies with or adheres to the building code standards established by another governing authority or regulatory framework.
-
B.
successorBuildingOnSite
chosen
Indicates that one building directly replaces another on the same physical site or location.
-
C.
constructionSite
Indicates that an entity is a location or area where construction work is actively taking place or is planned to occur.
-
D.
isBuildingOf
Indicates that one entity is a building that belongs to, houses, or is associated with another entity (such as an organization, institution, or complex).
-
E.
containsBuilding
Indicates that one location or area includes a building within its boundaries.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97dba57988190b786ffed55687a72 |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 5:44 p.m.