Triple
T8042987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Surrealist Group in Prague |
E187478
|
entity |
| Predicate | notableMember |
P10
|
FINISHED |
| Object | Toyen |
E706814
|
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: Toyen | Statement: [Surrealist Group in Prague, notableMember, Toyen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Toyen Context triple: [Surrealist Group in Prague, notableMember, Toyen]
-
A.
Toyen
chosen
Toyen was a Czech avant-garde painter and illustrator known for her distinctive contributions to surrealism and erotic art in 20th-century Europe.
-
B.
Tuyo
"Tuyo" is a bolero-style song by Rodrigo Amarante, best known as the haunting opening theme of the television series *Narcos*.
-
C.
Tose
Tose is the surname of Leonard Tose, the former owner of the Philadelphia Eagles NFL franchise.
-
D.
Tokkō
Tokkō was the colloquial name for Japan’s prewar and wartime Special Higher Police, a political police force tasked with suppressing dissent and ideological opposition.
-
E.
Takara
Takara is a Japanese toy company best known for creating and producing Transformers and other popular action figures.
- 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_69ca82b00cb48190b59a300f70e97bd7 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3f49dcfc81909ac7c93e19ad05c2 |
completed | March 31, 2026, 3:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63cdecc88190beac3976e7c47114 |
completed | April 1, 2026, 12:16 a.m. |
Created at: March 30, 2026, 5:23 p.m.