Triple
T10396709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deadwater Fell |
E245039
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Kudos |
E860455
|
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: Kudos | Statement: [Deadwater Fell, productionCompany, Kudos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kudos Context triple: [Deadwater Fell, productionCompany, Kudos]
-
A.
Kudos
chosen
Kudos is a British television production company known for creating acclaimed drama series such as "Broadchurch," "Spooks," and "Life on Mars."
-
B.
Acclaim
Acclaim is a virtual reality product or platform associated with the VR Commodore system.
-
C.
Praise
Praise is a 1998 Australian film directed by John Curran, adapted from Andrew McGahan’s novel, that explores a raw, intimate relationship between two misfit lovers.
-
D.
Thanks
"Thanks" is a film featuring Erika Christensen in a notable role.
-
E.
Laud
Laud is a notable English surname most famously borne by William Laud, the 17th-century Archbishop of Canterbury under King Charles I.
- 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9cf79348190975d6c1791e3b621 |
completed | April 7, 2026, 11:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d94af4ee6881909a36ee1a06a9d3e2 |
completed | April 10, 2026, 7:09 p.m. |
Created at: April 6, 2026, 12:06 p.m.