Triple
T19754230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | China Miéville |
E474462
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Railsea |
—
|
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: Railsea | Statement: [China Miéville, notableWork, Railsea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Railsea Context triple: [China Miéville, notableWork, Railsea]
-
A.
Railsea
chosen
Railsea is a 2012 young adult science fiction novel by China Miéville that reimagines Moby-Dick in a post-apocalyptic world of endless railroads and monstrous subterranean creatures.
-
B.
An tIúr
An tIúr is the Irish name for Newry, a city in Northern Ireland near the border with the Republic of Ireland.
-
C.
La Eile
"La Eile" is a song featured on the original Broadway cast recording of the musical *Footloose*, included on the album *I Can’t Stand Still*.
-
D.
Déise
Déise is a culturally distinct Irish-speaking region in County Waterford known for its strong preservation of traditional Gaelic language and heritage.
-
E.
Eir
Eir is a Norse goddess associated with the Aesir, renowned as a divine healer and patron of medicine.
- 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6529cae048190b4f8e6ba409bcf8e |
completed | April 20, 2026, 4:21 p.m. |
Created at: April 10, 2026, 1:48 p.m.