Triple

T4580348
Position Surface form Disambiguated ID Type / Status
Subject Amnesty International E101838 entity
Predicate abbreviation P43 FINISHED
Object AI E101838 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: AI | Statement: [Amnesty International, abbreviation, AI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AI
Context triple: [Amnesty International, abbreviation, AI]
  • A. AI chosen
    Amnesty International is a global non-governmental organization focused on protecting human rights and campaigning against abuses such as torture, unjust imprisonment, and the death penalty.
  • B. AI
    AI is Adobe Illustrator’s native vector graphics file format used to store and exchange editable artwork.
  • C. AI
    Allen Iverson is a Hall of Fame former NBA point guard and shooting guard renowned for his scoring ability, quickness, and cultural impact on basketball.
  • D. Ai
    Ai is a Chinese surname historically associated with the Jewish community of Kaifeng, reflecting their integration into broader Chinese society.
  • E. Ai
    Ai is an ancient Canaanite city mentioned in the Hebrew Bible, particularly in the Book of Joshua, as a site of early Israelite military campaigns.
  • 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_69bd43d4ce208190b53158c882b222e3 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd58e534708190a1ba9c5a29b3774d completed March 20, 2026, 2:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdd3f532dc81909b6c464defada832 completed March 20, 2026, 11:10 p.m.
Created at: March 20, 2026, 1:10 p.m.