Triple
T20608819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wiglaf |
E506390
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Beowulf (character) |
—
|
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: Beowulf (character) | Statement: [Wiglaf, associatedWith, Beowulf (character)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Beowulf (character) Context triple: [Wiglaf, associatedWith, Beowulf (character)]
-
A.
Beowulf (character)
chosen
Beowulf is the legendary Geatish hero and warrior of the Old English epic poem who battles the monster Grendel, Grendel’s mother, and a dragon.
-
B.
Beow
Beow is a legendary Danish king from early medieval tradition, often associated with the royal lineage featured in the Old English epic "Beowulf."
-
C.
Beow Lean
Beow Lean was a Buddhist monk and religious leader best known for establishing the renowned Kek Lok Si Temple in Penang, Malaysia.
-
D.
Beowulf Boritt
Beowulf Boritt is a Tony Award–winning American scenic designer known for his inventive and visually dynamic sets on Broadway and beyond.
-
E.
Beowulf’s foster-father
Beowulf’s foster-father is Hrethel, the Geatish king who raised the hero as his own grandson and heir in the Old English epic.
- 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_69e0b4bb2b4081908fa4a72444120f35 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aad5e53c8190b0add34ce9b31d57 |
completed | April 20, 2026, 10:38 p.m. |
Created at: April 16, 2026, 11:41 a.m.