Triple
T20914879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upper Palaeolithic |
E515045
|
entity |
| Predicate | geographicDistribution |
P2178
|
FINISHED |
| Object | Eurasia |
—
|
NE NERFINISHED |
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: Eurasia | Statement: [Upper Palaeolithic, geographicDistribution, Eurasia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eurasia Context triple: [Upper Palaeolithic, geographicDistribution, Eurasia]
-
A.
Eurasia
chosen
Eurasia is the vast combined continental landmass of Europe and Asia, forming the largest continuous land area on Earth.
-
B.
Asya
Asya is a common Russian diminutive form of the female given name Anastasia.
-
C.
Euravia
Euravia was the original name of the British charter airline that later became known as Britannia Airways.
-
D.
Asia–Europe
Asia–Europe is a major intercontinental shipping and trade route connecting key ports across the Asian and European continents.
-
E.
Afro-Eurasia
Afro-Eurasia is the vast continuous landmass comprising the continents of Africa, Europe, and Asia, forming the largest connected continental area on Earth.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4f9d5ec8190bb2bd27350ed341c |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6ec61a6ec81908d9e0629438d27c9 |
completed | April 21, 2026, 3:17 a.m. |
Created at: April 16, 2026, 12:48 p.m.