Triple
T20084241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Klingon Empire |
E500081
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Qo'noS |
—
|
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: Qo'noS | Statement: [Klingon Empire, capital, Qo'noS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Qo'noS Context triple: [Klingon Empire, capital, Qo'noS]
-
A.
Qo'noS
chosen
Qo'noS is the Klingon homeworld in the Star Trek universe, known for its warrior culture and as the seat of the Klingon Empire.
-
B.
Kono
Kono is a Japanese surname most prominently associated with politician Taro Kono, a leading figure in contemporary Japanese politics.
-
C.
Kono
Kono is a major Mande language spoken primarily in parts of West Africa, notably in Sierra Leone and neighboring regions.
-
D.
Kunka
Kunka is the original name of the Historic Walled Town of Cuenca, a UNESCO-listed medieval city in central Spain renowned for its dramatic clifftop setting and well-preserved architecture.
-
E.
Konosu
Konosu is a city in Saitama Prefecture, Japan, known for its traditional doll-making industry and large-scale seasonal flower displays.
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655a2d2c81908a6b8fd2f209a825 |
completed | April 20, 2026, 5:41 p.m. |
Created at: April 11, 2026, 3:41 p.m.