Triple
T9291719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matisse cut-outs |
E223533
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Icarus |
E223544
|
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: Icarus | Statement: [Matisse cut-outs, notableWork, Icarus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Icarus Context triple: [Matisse cut-outs, notableWork, Icarus]
-
A.
Icarus
chosen
Icarus is a figure from Greek mythology known for flying too close to the sun with wings made of feathers and wax, causing his fatal fall into the sea.
-
B.
ICARUS
ICARUS is a large liquid-argon time projection chamber neutrino detector designed to study neutrino properties and rare particle interactions.
-
C.
Phaethon
Phaethon is a figure in Greek mythology best known for disastrously attempting to drive the sun god’s chariot across the sky, leading to his death and the scorching of the earth.
-
D.
Ceyx
Ceyx is a figure from Greek mythology, a king of Trachis known for his tragic love story with Alcyone that led to their transformation into halcyon birds.
-
E.
L’envol d’Icare
L’envol d’Icare is a modernist ballet score by Igor Markevitch that reimagines the Greek myth of Icarus through innovative orchestration and rhythm.
- 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_69ca8422ddf881908a3f8f876c9f53aa |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd0866ff608190a07afac4afd0ec09 |
completed | April 1, 2026, 11:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b2381e2c8190acbecf97dea1200c |
completed | April 4, 2026, 6:39 a.m. |
Created at: March 30, 2026, 7:35 p.m.