Triple
T12121785
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | royal garrison of the Bastille |
E288712
|
entity |
| Predicate | associatedBuildingFunction |
P16394
|
FINISHED |
| Object | state prison |
—
|
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: state prison | Statement: [royal garrison of the Bastille, associatedBuildingFunction, state prison]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedBuildingFunction Context triple: [royal garrison of the Bastille, associatedBuildingFunction, state prison]
-
A.
adjacentBuildingFunction
Indicates that two buildings located next to each other have a specified functional relationship or usage connection.
-
B.
hasBuildingFunction
chosen
Indicates that a building is used for or serves a particular function or purpose.
-
C.
architectureAssociated
Indicates that there is a relationship or connection between an entity and a particular architectural style, feature, or practice.
-
D.
appliedToBuilding
Indicates that something (such as a process, treatment, regulation, or attribute) is directed toward, implemented on, or otherwise affects a building.
-
E.
seatBuildingFunction
Indicates that a building or structure serves a seating-related function, such as providing places for people to sit or be accommodated.
- 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_69d6ab4b5e4c81909950b17151eb0951 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d91841615c819097f20a7447a1b8f4 |
completed | April 10, 2026, 3:33 p.m. |
| PD | Predicate disambiguation | batch_69d91508f8008190b3a90ec0bf0953ca |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:49 p.m.