Triple
T10396718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deadwater Fell |
E245039
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Cush Jumbo |
E781258
|
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: Cush Jumbo | Statement: [Deadwater Fell, stars, Cush Jumbo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cush Jumbo Context triple: [Deadwater Fell, stars, Cush Jumbo]
-
A.
Cush Jumbo
chosen
Cush Jumbo is a British actress and writer best known for her acclaimed role as attorney Lucca Quinn on the television series "The Good Wife" and its spin-off "The Good Fight."
-
B.
Cush
Cush is an ancient biblical region and people, often identified with areas south of Egypt such as Nubia or Ethiopia.
-
C.
Negus
Negus is the 2010 studio album by American rapper and producer Mos Def (Yasiin Bey), known for its experimental, Afrocentric hip-hop sound and conceptual approach.
-
D.
Negus
Negus was a royal title used in Ethiopia for kings or rulers, ranking below the emperor.
-
E.
Zellig
Zellig is a given name most notably borne by Zellig Harris, an influential American linguist known for his work in structural linguistics and discourse analysis.
- 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_69d795cf331c8190b35caf3997dc29a3 |
completed | April 9, 2026, 12:04 p.m. |
Created at: April 6, 2026, 12:06 p.m.