Triple
T4517547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brazilian Adventure |
E103187
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Peter Fleming |
E18855
|
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: Peter Fleming | Statement: [Brazilian Adventure, featuresCharacter, Peter Fleming]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Fleming Context triple: [Brazilian Adventure, featuresCharacter, Peter Fleming]
-
A.
Peter Fleming
chosen
Peter Fleming was a British travel writer, journalist, and adventurer, best known for his travel books and for his work as a wartime intelligence officer.
-
B.
William Fleming
William Fleming is a relatively common personal name shared by multiple notable individuals across fields such as politics, education, and sports.
-
C.
Ian Fleming
Ian Fleming was a British author and journalist best known as the creator of the James Bond spy novels.
-
D.
Walter Connolly
Walter Connolly was an American character actor of the 1930s known for his comic and often blustery supporting roles in Hollywood films.
-
E.
Robert Fairthorne
Robert Fairthorne was a British information scientist and mathematician known for his influential work in documentation, information retrieval theory, and the early development of information science as a discipline.
- 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_69bd43dba59881908cf59b31df8c7ae1 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd572933408190b67c4ef6a7babe75 |
completed | March 20, 2026, 2:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdacd174c88190a186bc2ecc20fcd5 |
completed | March 20, 2026, 8:23 p.m. |
Created at: March 20, 2026, 1:02 p.m.