Triple
T19974989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hero of Twilight |
E493665
|
entity |
| Predicate | companion |
P2932
|
FINISHED |
| Object | Epona |
—
|
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: Epona | Statement: [Hero of Twilight, companion, Epona]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Epona Context triple: [Hero of Twilight, companion, Epona]
-
A.
Epona
chosen
Epona is Link’s loyal horse in The Legend of Zelda series, known for helping him traverse vast landscapes quickly and reliably.
-
B.
Briosa
Briosa is the popular nickname of Associação Académica de Coimbra’s football team, a historic Portuguese club closely linked to the University of Coimbra and its student culture.
-
C.
Cavalla
Cavalla is a historic port city on the Aegean Sea in northern Greece, known today as Kavala and noted for its strategic location and Ottoman-era heritage.
-
D.
Gingilos
Gingilos is a prominent mountain peak in western Crete, Greece, known for its rugged terrain, scenic hiking routes, and expansive views over the surrounding Lefka Ori range and the Libyan Sea.
-
E.
Vacallo
Vacallo is a small municipality in the canton of Ticino in southern Switzerland, located near the Italian border.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65bcca5088190b523584d11799400 |
completed | April 20, 2026, 5:01 p.m. |
Created at: April 11, 2026, 3:24 p.m.