Triple

T489767
Position Surface form Disambiguated ID Type / Status
Subject Harold E9958 entity
Predicate relatedName P3889 FINISHED
Object Harald E25389 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: Harald | Statement: [Harold, relatedName, Harald]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harald
Context triple: [Harold, relatedName, Harald]
  • A. Harold Bluetooth
    Harold Bluetooth was a 10th-century king of Denmark and Norway known for uniting much of Scandinavia and for inspiring the name of the modern Bluetooth wireless technology standard.
  • B. Haakon VII of Norway
    Haakon VII of Norway was the first king of an independent modern Norway and a widely respected constitutional monarch who led the nation through World War II.
  • C. Edvard
    Edvard is a given name, commonly used in Scandinavian and some European countries, that corresponds to the English name Edward.
  • D. Harald V of Norway chosen
    Harald V of Norway is the constitutional monarch and head of state of Norway, known for his long reign and dedication to public service and national unity.
  • E. Rollo
    Rollo was a Viking leader who became the first ruler of Normandy, laying the foundations for the Norman people and their later influence in European history.
  • 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_69a2e802e2908190ab17c9479e0b6412 completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2f0e0a9648190b6a3b2da3a3b51e6 completed Feb. 28, 2026, 1:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69a47d2a78a48190ac5a1e7f57f9dbd1 completed March 1, 2026, 5:53 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.