Triple
T9510022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dominic Cooper |
E229367
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object | Sky |
E338790
|
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: Sky | Statement: [Dominic Cooper, portrayed, Sky]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sky Context triple: [Dominic Cooper, portrayed, Sky]
-
A.
Sky
chosen
Sky is a charming and supportive young man from the musical and film "Mamma Mia!", known for his relationship with Sophie Sheridan and their plans to build a life together.
-
B.
Sky
"Sky" is a popular track by American rapper Playboi Carti, known for its hypnotic production and viral presence within the cloud rap and trap scenes.
-
C.
Sky
Sky is a major British media and telecommunications company best known for its satellite television services and original programming.
-
D.
SKY
SKY is the ICAO airline designator used to identify Skymark Airlines in international aviation operations.
-
E.
Sky Light
Sky Light is an abstract painting by American artist Alma Thomas, characterized by her signature mosaic-like blocks of color evoking light and atmospheric movement.
- 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_69ca847611c48190a28c028644198c75 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9857058881909e0a40e2024a7b4c |
completed | April 1, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d13a31600c8190a4a7ecb5231caa36 |
completed | April 4, 2026, 4:20 p.m. |
Created at: March 30, 2026, 7:58 p.m.