Triple
T10775490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bibliothèque Sainte-Geneviève |
E254185
|
entity |
| Predicate | readingRoomCapacity |
P56142
|
FINISHED |
| Object | approximately 800 seats |
—
|
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: approximately 800 seats | Statement: [Bibliothèque Sainte-Geneviève, readingRoomCapacity, approximately 800 seats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: readingRoomCapacity Context triple: [Bibliothèque Sainte-Geneviève, readingRoomCapacity, approximately 800 seats]
-
A.
hasReadingRoomCapacity
chosen
Indicates the maximum number of people that can be accommodated in a reading room at one time.
-
B.
hasReadingRoom
Indicates that a place or facility includes a designated reading room area available for use.
-
C.
librarySystemSize
Indicates the overall scale or capacity of a library system, such as the number of branches, items, or resources it encompasses.
-
D.
standingCapacity
Indicates the maximum number of people that are allowed or able to stand in a given space or vehicle.
-
E.
hasReadingRoomType
Indicates that an entity (such as a facility or building) has a specific type or category of reading room.
- 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7329cc6c881908f827edff941d456 |
completed | April 9, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69d6f31455648190b5c24690487b1b54 |
completed | April 9, 2026, 12:30 a.m. |
Created at: April 8, 2026, 9:16 p.m.