Triple
T31713608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Governor of Annapolis Royal |
E809394
|
entity |
| Predicate | seatEstablishedAfter |
P1102
|
FINISHED |
| Object | Siege of Port Royal (1710) |
—
|
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: Siege of Port Royal (1710) | Statement: [Governor of Annapolis Royal, seatEstablishedAfter, Siege of Port Royal (1710)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seatEstablishedAfter Context triple: [Governor of Annapolis Royal, seatEstablishedAfter, Siege of Port Royal (1710)]
-
A.
eraOfEstablishment
Indicates the time period or historical era during which an entity was founded or established.
-
B.
foundedAfter
chosen
Indicates that one entity was founded at a later time than another entity.
-
C.
placeEstablished
Indicates that an entity was founded, created, or formally established at a particular place or location.
-
D.
foundedInOrBefore
Indicates that the founding of one entity occurred in a specified year or any earlier year.
-
E.
hasYearOfEstablishment
Indicates the specific year in which an entity was founded, created, or formally established.
- 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_69f348df4e048190a4a5a9932ada78d6 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:16 p.m.