Triple
T15035963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nyssa |
E378476
|
entity |
| Predicate | appearsInStory |
P795
|
FINISHED |
| Object | Kinda |
E1132710
|
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: Kinda | Statement: [Nyssa, appearsInStory, Kinda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kinda Context triple: [Nyssa, appearsInStory, Kinda]
-
A.
Kinda
chosen
Kinda is a 1982 Doctor Who television serial from the classic series, featuring the Fifth Doctor in a psychological and philosophical science-fiction story set on the planet Deva Loka.
-
B.
Some Kinda
"Some Kinda" is a neo-soul/R&B album by American singer-songwriter Dwele, showcasing his smooth vocals and jazz-influenced production.
-
C.
Special Kinda
Special Kinda is a song featured on Tiwa Savage’s EP "Water & Garri."
-
D.
Dondas
Dondas is an alternative form or variant of the name Dundas, which is used for various places, people, and institutions, particularly in English-speaking regions.
-
E.
Gençler
Gençler is a common nickname for the Turkish football club Gençlerbirliği S.K., based in Ankara and known for competing in the country's professional leagues.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded82b29948190acda49cbec3f927a |
completed | April 15, 2026, 12:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5b75c04819085996a7f88ab6c38 |
completed | May 9, 2026, 3:10 a.m. |
Created at: April 10, 2026, 2:59 a.m.