Triple
T29702198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peada of Mercia |
E751517
|
entity |
| Predicate | possiblyKilledBy |
P4646
|
FINISHED |
| Object | Alhflæd of Northumbria |
—
|
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: Alhflæd of Northumbria | Statement: [Peada of Mercia, possiblyKilledBy, Alhflæd of Northumbria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possiblyKilledBy Context triple: [Peada of Mercia, possiblyKilledBy, Alhflæd of Northumbria]
-
A.
killedBy
chosen
Indicates that one entity caused the death of another entity.
-
B.
killedBecauseOf
Indicates that one entity killed another specifically due to a particular reason, motive, or triggering factor associated with that other entity or a related circumstance.
-
C.
killedDuring
Indicates that one entity caused the death of another entity in the course of, or as part of, a specified event or time period.
-
D.
isKilledTo
Indicates that one entity is killed as a consequence or objective of an action performed by another entity.
-
E.
killedOnBehalfOf
Indicates that one entity carried out a killing as a representative of, or in service to, another entity.
- 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_69f0d6266f8481909e70bb41cda18587 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 28, 2026, 7:24 p.m.