Triple
T333744
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henri Matisse |
E6678
|
entity |
| Predicate | workLocation |
P7
|
FINISHED |
| Object | Nice |
E2387
|
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: Nice | Statement: [Henri Matisse, workLocation, Nice]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nice Context triple: [Henri Matisse, workLocation, Nice]
-
A.
Nice
chosen
Nice is a prominent Mediterranean coastal city on the French Riviera, known for its mild climate, beaches, and vibrant cultural life.
-
B.
Nice Carnival
Nice Carnival is one of the world’s major and oldest carnival festivals, held annually in the French Riviera city of Nice and known for its elaborate parades, floats, and flower battles.
-
C.
NI
NI is the vehicle registration code used on license plates for the German federal state of Lower Saxony.
-
D.
Alright
"Alright" is a song featured on John Legend's debut studio album "Get Lifted."
-
E.
nēnē
The nēnē, or Hawaiian goose, is a rare, medium-sized goose species endemic to Hawaii and renowned as a conservation success story after nearing extinction.
- 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_69a2e79434908190a9d5afe415153ad9 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eac4d9d081908a624464e450fb0e |
completed | Feb. 28, 2026, 1:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3d7e6f9408190a4c17c25a57625cf |
completed | March 1, 2026, 6:08 a.m. |
Created at: Feb. 28, 2026, 1:08 p.m.