Triple
T17512124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roma Ryan |
E426474
|
entity |
| Predicate | writingLanguage |
P2245
|
FINISHED |
| Object | Loxian |
—
|
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: Loxian | Statement: [Roma Ryan, writingLanguage, Loxian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Loxian Context triple: [Roma Ryan, writingLanguage, Loxian]
-
A.
Loxian
chosen
Loxian is a fictional constructed language created by Enya and her collaborators, used in some of her songs to evoke a mystical, otherworldly atmosphere.
-
B.
Tevanian
Tevanian is the surname of Avie Tevanian, a prominent software engineer known for his work on the Mach kernel and as a former Apple executive.
-
C.
Kamassian
Kamassian is an extinct Samoyedic language formerly spoken in parts of Siberia by the Kamassian people.
-
D.
Tamaranean
Tamaraneans are a fictional alien warrior race from the DC Comics universe known for their orange skin, ability to absorb solar energy, and powers of flight and energy projection.
-
E.
Toisanese
Toisanese is a Yue Chinese dialect spoken primarily by people from Taishan in Guangdong, historically influential among early Chinese diaspora communities in North America.
- 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_69d889dd9164819087b1dc3c9240c870 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4525c21c88190a9394c4bce006a38 |
completed | April 19, 2026, 3:56 a.m. |
Created at: April 10, 2026, 5:48 a.m.