Triple
T18587128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Æthelred Mucel |
E454262
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Ealhswith |
—
|
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: Ealhswith | Statement: [Æthelred Mucel, relative, Ealhswith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ealhswith Context triple: [Æthelred Mucel, relative, Ealhswith]
-
A.
Ealhswith
chosen
Ealhswith was a 9th-century Anglo-Saxon noblewoman best known as the wife of King Alfred the Great and the mother of several English kings and queens.
-
B.
Eowa of Mercia
Eowa of Mercia was a 7th-century Mercian prince, likely a brother or close kinsman of King Penda, who may have briefly ruled part of Mercia before dying at the Battle of Maserfield.
-
C.
Eadflæd
Eadflæd was a daughter of King Edward the Elder of England, belonging to the royal House of Wessex in the early 10th century.
-
D.
Ælfflæd
Ælfflæd was a 10th-century English noblewoman who became queen consort of the Anglo-Saxon king Edward the Elder.
-
E.
Æthelgyth
Æthelgyth was a daughter of Ealhswith, the wife of Alfred the Great, and thus a member of the royal family of Wessex in early medieval England.
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e545b2f20481908da74447cd08d5bd |
completed | April 19, 2026, 9:14 p.m. |
Created at: April 10, 2026, 11:44 a.m.