Triple
T2609388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Order of Saint Patrick |
E58737
|
entity |
| Predicate | lastAppointmentDate |
P6167
|
FINISHED |
| Object | 1936 |
—
|
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: 1936 | Statement: [Order of Saint Patrick, lastAppointmentDate, 1936]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastAppointmentDate Context triple: [Order of Saint Patrick, lastAppointmentDate, 1936]
-
A.
lastSessionDate
Indicates the date on which the most recent session involving the entity took place.
-
B.
lastAppointments
chosen
Indicates that the referenced appointments are the most recent ones associated with a given entity or context.
-
C.
lastEntryDate
Indicates the date on which the most recent entry, record, or update associated with the subject occurred.
-
D.
lastTestDate
Indicates the date on which the most recent test associated with the entity was conducted.
-
E.
lastSignalDate
Indicates the date on which the most recent signal or communication event occurred between the related entities.
- 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_69ab4ac3523881909679750c9f8c2dec |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd8def9bc8190b2e013abffc7b191 |
completed | March 7, 2026, 7:50 a.m. |
| PD | Predicate disambiguation | batch_69abd80ab7248190ba06ba14fe4c5638 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:49 p.m.