Triple

T28284099
Position Surface form Disambiguated ID Type / Status
Subject Xin Wudai Shi E713231 entity
Predicate includesStateType P198356 FINISHED
Object Ten Kingdoms
The Ten Kingdoms were a group of short-lived, regional dynasties that ruled parts of southern China during the politically fragmented Five Dynasties and Ten Kingdoms period (907–979 CE).
 E1810720 NE FINISHED

How this triple was built (3 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: Ten Kingdoms | Statement: [Xin Wudai Shi, includesStateType, Ten Kingdoms]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ten Kingdoms
Triple: [Xin Wudai Shi, includesStateType, Ten Kingdoms]
Generated description
The Ten Kingdoms were a group of short-lived, regional dynasties that ruled parts of southern China during the politically fragmented Five Dynasties and Ten Kingdoms period (907–979 CE).
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: includesStateType
Context triple: [Xin Wudai Shi, includesStateType, Ten Kingdoms]
  • A. includesStateOrProvince
    Indicates that one entity geographically contains or encompasses a specific state or province within its boundaries.
  • B. stateIncludes
    Indicates that a given state encompasses, contains, or has within its boundaries another specified entity or region.
  • C. includesJurisdictionType
    Indicates that a given entity’s authority, scope, or coverage extends to and encompasses a specified type of jurisdiction.
  • D. includesSovereignState
    Indicates that one entity encompasses or contains a sovereign state within its scope, membership, or composition.
  • E. includesMostOfState
    Indicates that one geographic or political entity contains the majority of the area or extent of a given state within its boundaries.
  • F. None of above. chosen

Provenance (7 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_69efb52371d88190a1381c4e58a3b731 completed April 27, 2026, 7:12 p.m.
NER Named-entity recognition batch_69fedfd913f48190bdcd450980868d9a completed May 9, 2026, 7:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a160728a9108190b774efc094320cdb completed May 26, 2026, 8:48 p.m.
NEDg Description generation batch_6a1613ef6698819089eb6e89c8fff844 completed May 26, 2026, 9:43 p.m.
NED2 Entity disambiguation (via description) batch_6a1614512f9881908fa9fe919e32a1e4 completed May 26, 2026, 9:44 p.m.
PD Predicate disambiguation batch_69fedf58c6e88190821a7156054c9086 completed May 9, 2026, 7:16 a.m.
PDg Predicate description generation batch_69fedfd850ec81909b55f90dc850167e completed May 9, 2026, 7:18 a.m.
Created at: April 27, 2026, 11:25 p.m.