Triple
T28504258
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archbishop of Hartford |
E721326
|
entity |
| Predicate | officeCreatedWithin |
P4759
|
FINISHED |
| Object | Roman Catholic hierarchy in the United States |
—
|
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: Roman Catholic hierarchy in the United States | Statement: [Archbishop of Hartford, officeCreatedWithin, Roman Catholic hierarchy in the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeCreatedWithin Context triple: [Archbishop of Hartford, officeCreatedWithin, Roman Catholic hierarchy in the United States]
-
A.
officeCreatedOn
Indicates the date on which an office was formally established or created.
-
B.
officeCreatedInPeriod
Indicates that an office was created during a specified time period.
-
C.
officeCreatedUnder
chosen
Indicates that an office was established or formed under the authority, jurisdiction, or organizational structure of a particular entity or governing body.
-
D.
officeCreatedFor
Indicates that an office or position was established specifically to serve, represent, or support a particular entity.
-
E.
officeCreatedAlongWith
Indicates that an office was established at the same time as another specified entity, event, or office.
- 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_69f01a5c072081908c7b04bcf6478da9 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: April 28, 2026, 3:08 a.m.