Triple
T36306167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Icon of Our Lady of Perpetual Help |
E893947
|
entity |
| Predicate | entrustedToYear |
P179618
|
FINISHED |
| Object | 1866 |
—
|
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: 1866 | Statement: [Icon of Our Lady of Perpetual Help, entrustedToYear, 1866]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: entrustedToYear Context triple: [Icon of Our Lady of Perpetual Help, entrustedToYear, 1866]
-
A.
iconEntrustedYear
chosen
Indicates the year in which an icon was formally entrusted or assigned to someone or something.
-
B.
commitmentPeriodEndYear
Indicates the year in which a specified commitment period concludes.
-
C.
agreementYear
Indicates the calendar year in which an agreement between the related entities was made, signed, or came into effect.
-
D.
claimedYear
Indicates the year that is asserted or reported as being associated with an event, status, or fact, regardless of whether it is verified.
-
E.
specifiedYear
Indicates that a particular year has been explicitly designated or identified in relation to the subject.
- 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_69f76e4c1b248190b10667d0213537fe |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7ba6d06f48190a71b5a2f19e2232f |
completed | May 3, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a4aad48190a62e41c5e39339d9 |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:09 p.m.