Triple
T10226473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Théoden (film character) |
E243216
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Théodred |
E747679
|
NE 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: Théodred | Statement: [King Théoden (film character), relative, Théodred]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Théodred Context triple: [King Théoden (film character), relative, Théodred]
-
A.
Théodred
chosen
Théodred is a character in J.R.R. Tolkien's Middle-earth legendarium, the son and heir of King Théoden of Rohan who is slain in battle before the War of the Ring.
-
B.
Wiglaf
Wiglaf is a loyal warrior and the only thane who remains to aid the hero Beowulf in his final battle with the dragon in the Old English epic poem "Beowulf."
-
C.
Hrothmund
Hrothmund is a legendary Danish prince from the Old English epic Beowulf, known as one of King Hrothgar’s sons and a member of the Scylding royal line.
-
D.
Chlothsind
Chlothsind was a Frankish princess, daughter of King Chlothar I, who became queen of the Lombards through her marriage to King Alboin.
-
E.
Hygelac
Hygelac is the legendary king of the Geats and uncle to the hero Beowulf in the Old English epic poem.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d381b0f97c819085c9b45799a5fb7c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d1f9cf6c81909a6b9e9b9d0a79fe |
completed | April 7, 2026, 9:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f71fb4048190a36f1fe499729332 |
completed | April 9, 2026, 12:47 a.m. |
Created at: April 6, 2026, 11:17 a.m.