Triple
T25772292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TOSSPX |
E649051
|
entity |
| Predicate | headquartersSharedWith |
P31031
|
FINISHED |
| Object | Society of Saint Pius X general house |
—
|
NE NERFINISHED |
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: Society of Saint Pius X general house | Statement: [TOSSPX, headquartersSharedWith, Society of Saint Pius X general house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: headquartersSharedWith Context triple: [TOSSPX, headquartersSharedWith, Society of Saint Pius X general house]
-
A.
homeGroundSharedWith
Indicates that two teams or organizations use the same venue or location as their home ground.
-
B.
sharesHeadquartersWith
chosen
Indicates that two entities have their main headquarters located in the same place.
-
C.
sharesMembersWith
Indicates that two groups or collections have one or more members in common.
-
D.
sharesRateCenterStructureWith
Indicates that two telecommunications entities are associated with and utilize the same underlying rate center infrastructure or configuration.
-
E.
sharesAdministrationWith
Indicates that two entities are jointly managed, governed, or overseen by the same administrative body or authority.
- 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_69e7ab333b508190b6d708d8d9a328ed |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f5fe5a0ec0819085a2c7c652de294f |
completed | May 2, 2026, 1:38 p.m. |
| PD | Predicate disambiguation | batch_69f4938b960081909b53c074a3e0c7c2 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 5:30 a.m.