Triple
T34693799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | siege of Aberystwyth Castle |
E890971
|
entity |
| Predicate | occursInYearRange |
P149098
|
FINISHED |
| Object | c. 1404–1408 |
—
|
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: c. 1404–1408 | Statement: [siege of Aberystwyth Castle, occursInYearRange, c. 1404–1408]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occursInYearRange Context triple: [siege of Aberystwyth Castle, occursInYearRange, c. 1404–1408]
-
A.
occurredBetween
Indicates that an event or action took place within the time interval defined by two temporal boundaries.
-
B.
occursInGregorianPeriod
Indicates that an event or occurrence takes place within a specified time interval defined in the Gregorian calendar.
-
C.
hasPartInYear
Indicates that something includes or contains a specific part, component, or segment that is associated with a particular year.
-
D.
chronologicallyBetween
Indicates that one event or time point occurs after a first reference point and before a second reference point in temporal order.
-
E.
approximateYearRange
chosen
Indicates that the associated time span is not exact but falls within an estimated or approximate range of years.
- 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_69f349db7ab8819086808e833f472871 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f723549ac8819088816d0c96e28251 |
completed | May 3, 2026, 10:28 a.m. |
| PD | Predicate disambiguation | batch_69f72157af108190880317a62e634bb0 |
completed | May 3, 2026, 10:20 a.m. |
Created at: May 1, 2026, 2:05 a.m.