Triple
T4286302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Willow Ufgood |
E97276
|
entity |
| Predicate | ally |
P4662
|
FINISHED |
| Object | Sorsha |
E416856
|
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: Sorsha | Statement: [Willow Ufgood, ally, Sorsha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sorsha Context triple: [Willow Ufgood, ally, Sorsha]
-
A.
Sorsha
chosen
Sorsha is a warrior princess from the fantasy film "Willow" who initially serves her evil mother Queen Bavmorda before ultimately turning against her.
-
B.
Romeyka
Romeyka is an endangered Greek dialect spoken mainly in northeastern Turkey, notable for preserving many archaic features of Ancient Greek.
-
C.
Rositsa
Rositsa is a river in northern Bulgaria that serves as a significant tributary of the Yantra River.
-
D.
Violanta
Violanta is a one-act opera by Erich Wolfgang Korngold, known for its lush late-Romantic score and psychologically intense drama set in Renaissance Venice.
-
E.
Vladimira
Vladimira is a feminine given name, primarily used in Slavic cultures, derived from the male name Vladimir.
- 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_69b3454595848190a0e6bbb6a2bea040 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3505d23d88190a638f2cc2acee9ee |
completed | March 12, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5b7c657b08190b96135c34622e559 |
completed | March 14, 2026, 7:32 p.m. |
Created at: March 12, 2026, 11:08 p.m.