Triple

T27959580
Position Surface form Disambiguated ID Type / Status
Subject Liu Hong (alleged father of Liu Bei) E704542 entity
Predicate relationshipClaim P200767 FINISHED
Object claimed to be father of Liu Bei in some sources 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: claimed to be father of Liu Bei in some sources | Statement: [Liu Hong (alleged father of Liu Bei), relationshipClaim, claimed to be father of Liu Bei in some sources]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relationshipClaim
Context triple: [Liu Hong (alleged father of Liu Bei), relationshipClaim, claimed to be father of Liu Bei in some sources]
  • A. relationshipTarget
    Indicates that an entity is the object or recipient toward which a specified relationship is directed.
  • B. relationshipType
    Indicates the specific kind of relationship that exists between two or more entities.
  • C. haveRelationshipWith
    Indicates that one entity is in some form of defined relationship or association with another entity.
  • D. relationshipEnd
    Indicates that a previously existing relationship between entities has been terminated or has come to an end.
  • E. relationshipContext
    Indicates the situational or social setting in which a relationship between entities exists or occurs.
  • F. None of above. chosen

Provenance (4 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_69ef841061e48190b5570f9562f7434d completed April 27, 2026, 3:43 p.m.
NER Named-entity recognition batch_69ffac35ac5481908b6bdfd5bbe8c76e completed May 9, 2026, 9:50 p.m.
PD Predicate disambiguation batch_69ffabbfd2548190964c851496bbbaee completed May 9, 2026, 9:48 p.m.
PDg Predicate description generation batch_69ffac34c5948190be36de5781d91da3 completed May 9, 2026, 9:50 p.m.
Created at: April 27, 2026, 7:30 p.m.