Triple
T7055850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avro Anson |
E164088
|
entity |
| Predicate | manufacturer |
P490
|
FINISHED |
| Object | Avro |
E113414
|
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: Avro | Statement: [Avro Anson, manufacturer, Avro]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Avro Context triple: [Avro Anson, manufacturer, Avro]
-
A.
Avro
Avro is a row-oriented, schema-based data serialization format commonly used in big data processing and storage systems.
-
B.
Avro
chosen
Avro was a British aircraft manufacturer best known for producing iconic military aircraft such as the Avro Lancaster bomber during the 20th century.
-
C.
Hawker
Hawker is a surname of English origin borne by various notable individuals across fields such as aviation, politics, and the arts.
-
D.
de Havilland
De Havilland is the distinguished Anglo-French family name shared by Hollywood actresses Joan Fontaine and her sister Olivia de Havilland.
-
E.
Fairey
Fairey is the surname of American contemporary street artist and graphic designer Shepard Fairey, known for his iconic "Obey Giant" campaign and the Barack Obama "Hope" poster.
- 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_69c68861678881909961ddf4d779f750 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e269050c81908c186609a8a7bcf9 |
completed | March 27, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7889ddd488190b1e55828909133eb |
completed | March 28, 2026, 7:51 a.m. |
Created at: March 27, 2026, 2:38 p.m.