Triple
T21260726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Ashdown (871) |
E523990
|
entity |
| Predicate | commander |
P1061
|
FINISHED |
| Object | Bagsecg |
—
|
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: Bagsecg | Statement: [Battle of Ashdown (871), commander, Bagsecg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bagsecg Context triple: [Battle of Ashdown (871), commander, Bagsecg]
-
A.
Bagsecg
chosen
Bagsecg was a 9th-century Viking war leader and king who played a major role in the Norse invasions of Anglo-Saxon England.
-
B.
BSEC
BSEC is a regional intergovernmental organization that promotes economic cooperation and development among countries in the Black Sea region.
-
C.
Seco
Seco is Switzerland’s State Secretariat for Economic Affairs, responsible for national and international economic policy, labor market issues, and trade promotion.
-
D.
SECAmb
SECAmb is the National Health Service ambulance trust responsible for providing emergency medical services across the South East of England.
-
E.
GateKeeper
GateKeeper is a steel wing roller coaster at Cedar Point in Ohio, renowned for its record-breaking inversions and dramatic keyhole elements, designed by Swiss manufacturer Bolliger & Mabillard.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b5156d7881909bd4f83676590715 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735e6a0448190ad412a8fcbbd8ff0 |
completed | April 21, 2026, 8:31 a.m. |
Created at: April 16, 2026, 3:59 p.m.