Triple
T8170963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hôtel de Sully |
E190816
|
entity |
| Predicate | hasInnerSpace |
P6655
|
FINISHED |
| Object | private garden |
—
|
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: private garden | Statement: [Hôtel de Sully, hasInnerSpace, private garden]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInnerSpace Context triple: [Hôtel de Sully, hasInnerSpace, private garden]
-
A.
hasCentralSpace
Indicates that an entity includes or is characterized by a primary, central area or space within its overall structure.
-
B.
hasEmptyInterior
Indicates that the interior of an entity is completely hollow or contains no material.
-
C.
hasPublicSpaceAlong
Indicates that a public space (such as a park, plaza, or walkway) is located adjacent to or runs alongside the referenced feature or element.
-
D.
hasInteriorFeature
chosen
Indicates that an entity contains or includes a specific feature within its interior space.
-
E.
hasSecondarySpace
Indicates that an entity possesses or is associated with an additional, subordinate, or auxiliary space beyond its primary one.
- 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_69ca82c1c0a08190bf8692b4d91a03ca |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb48056d0c819094575090a41e0083 |
completed | March 31, 2026, 4:05 a.m. |
| PD | Predicate disambiguation | batch_69cb36a4c40c81909f60aef0e1624c13 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:39 p.m.