Triple

T23016107
Position Surface form Disambiguated ID Type / Status
Subject Liu Xia E573031 entity
Predicate causeOfHouseArrest P94805 FINISHED
Object imprisonment of her husband Liu Xiaobo LITERAL 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: imprisonment of her husband Liu Xiaobo | Statement: [Liu Xia, causeOfHouseArrest, imprisonment of her husband Liu Xiaobo]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: causeOfHouseArrest
Context triple: [Liu Xia, causeOfHouseArrest, imprisonment of her husband Liu Xiaobo]
  • A. placedUnderHouseArrest
    Indicates that an authority has confined an entity to a specified residence, restricting their freedom of movement as a form of legal or disciplinary control.
  • B. hasReasonForArrest chosen
    Indicates that an arrest is associated with a specific reason or cause.
  • C. arrestedFor
    Indicates that an authority has taken someone into custody because they are suspected or accused of committing a specified offense or wrongdoing.
  • D. causeOfLegalCondemnation
    Indicates that one entity is the reason or basis for another entity being legally condemned, judged guilty, or subjected to legal penalties.
  • E. reasonForConviction
    Indicates the specific offense or legal basis for which an individual was found guilty or convicted.
  • F. None of above.

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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183e4dcd48190b2b1c2ab43205e41 completed April 29, 2026, 4:07 a.m.
PD Predicate disambiguation batch_69ef3b9cd5488190bcd23183179f48cd completed April 27, 2026, 10:34 a.m.
Created at: April 17, 2026, 3:51 p.m.