Triple
T37436668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cristóbal López Romero |
E930291
|
entity |
| Predicate | partOfOrder |
P203412
|
FINISHED |
| Object | Society of Saint Francis de Sales |
—
|
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 Francis de Sales | Statement: [Cristóbal López Romero, partOfOrder, Society of Saint Francis de Sales]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfOrder Context triple: [Cristóbal López Romero, partOfOrder, Society of Saint Francis de Sales]
-
A.
partOfCollection
Indicates that an entity belongs to, or is included within, a larger collection or set.
-
B.
partOfSingle
Indicates that one entity is a component or member of exactly one specific whole or collection, and not shared among multiple such wholes.
-
C.
partOfPackage
Indicates that one entity is included as a component or element within a larger package or bundle.
-
D.
partOfType
Indicates that one entity represents a component, segment, or subset that belongs to or is included within the type or category represented by another entity.
-
E.
originallyBelongedToOrder
Indicates that an entity was previously a member of or associated with a particular order, but is no longer.
- F. None of above. chosen
Provenance (4 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_69f76ebfdcb8819098562ff3db673b04 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a017590e01c8190b985bb50cc6cd605 |
completed | May 11, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_6a0175406b348190a5809b5f3497d46f |
completed | May 11, 2026, 6:20 a.m. |
| PDg | Predicate description generation | batch_6a01758ff6d0819087730892b3ea1c75 |
completed | May 11, 2026, 6:22 a.m. |
Created at: May 3, 2026, 4:17 p.m.