Triple
T10215879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Théoden |
E242439
|
entity |
| Predicate | predecessor |
P97
|
FINISHED |
| Object | Thengel |
E850661
|
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: Thengel | Statement: [Théoden, predecessor, Thengel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thengel Context triple: [Théoden, predecessor, Thengel]
-
A.
Thengel
chosen
Thengel is a King of Rohan from J.R.R. Tolkien's Middle-earth legendarium, known for restoring strength and order to the realm after a period of decline.
-
B.
Thortan
Thortan is the historical site in Armenia traditionally regarded as the place where Saint Gregory the Illuminator, the patron saint and first official head of the Armenian Apostolic Church, died.
-
C.
Thrym
Thrym is a giant (jötunn) from Norse mythology best known for demanding the goddess Freyja as his bride in exchange for returning Thor’s stolen hammer.
-
D.
Loken
Loken is a surname most notably associated with American actress and model Kristanna Loken.
-
E.
Mardöll
Mardöll is an epithet of the Norse goddess Freyja, highlighting her radiant, jewel-like beauty and association with love and fertility.
- 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d3aa2894d0819095704449ecc2db6c |
completed | April 6, 2026, 12:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f6f4d0cc8190ae41277b15b3012d |
completed | April 9, 2026, 12:46 a.m. |
Created at: April 6, 2026, 11:05 a.m.