Triple
T6908065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theory of Colours |
E159859
|
entity |
| Predicate | publisher |
P29
|
FINISHED |
| Object | Cotta |
E145367
|
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: Cotta | Statement: [Theory of Colours, publisher, Cotta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cotta Context triple: [Theory of Colours, publisher, Cotta]
-
A.
Cotta
chosen
Cotta is a German publishing house historically known for issuing influential literary and philosophical works, including those of major figures like Goethe and Schiller.
-
B.
Munychus
Munychus is a minor figure in Greek mythology known primarily as a son of the Athenian hero Theseus.
-
C.
Cocceius
Cocceius is the family name of the Roman imperial dynasty to which the emperor Nerva belonged.
-
D.
Gaius Aurelius Cotta
Gaius Aurelius Cotta was a Roman statesman and consul of the 3rd century BC, noted for his role in Roman politics and military affairs.
-
E.
Aristo
Aristo is an AI research project by the Allen Institute for Artificial Intelligence focused on solving standardized science and math exams using natural language understanding and reasoning.
- 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_69c68839ccb88190b4aa5cc1aca3448f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d9bd7b3c8190842eb83679c322d5 |
completed | March 27, 2026, 7:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7617d81288190b38a67552f228933 |
completed | March 28, 2026, 5:05 a.m. |
Created at: March 27, 2026, 2:25 p.m.