Triple
T37727020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Findláech of Moray |
E940048
|
entity |
| Predicate | approximateCenturyOfDeath |
P3888
|
FINISHED |
| Object | 11th century |
—
|
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: 11th century | Statement: [Findláech of Moray, approximateCenturyOfDeath, 11th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateCenturyOfDeath Context triple: [Findláech of Moray, approximateCenturyOfDeath, 11th century]
-
A.
centuryOfDeath
Indicates the specific century during which an entity (typically a person) died.
-
B.
diedInCentury
chosen
Indicates that an entity’s death occurred during a specified century.
-
C.
approximatePeakCentury
Indicates the century in which something (such as influence, activity, or prominence) most likely reached its highest level, expressed as an approximate rather than exact peak time.
-
D.
approximateStartCentury
Indicates the century in which something is estimated or roughly believed to have begun.
-
E.
allegedDeathCentury
Indicates the century in which an entity is claimed or believed to have died, without asserting that the death is historically verified.
- 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_69f76edefd048190a32212c5c3919531 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffcb5536d88190bfc2e00b854cacfb |
completed | May 10, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69ffc900c2a081909dea04aa60566923 |
completed | May 9, 2026, 11:53 p.m. |
Created at: May 3, 2026, 4:18 p.m.