Triple

T4737716
Position Surface form Disambiguated ID Type / Status
Subject Hussein Onn E105164 entity
Predicate honorificTitle P2097 FINISHED
Object Tun
Tun is the highest federal title of honor in Malaysia, bestowed by the Yang di-Pertuan Agong for extraordinary service to the nation.
E465556 NE FINISHED

How this triple was built (4 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: Tun | Statement: [Hussein Onn, honorificTitle, Tun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tun
Context triple: [Hussein Onn, honorificTitle, Tun]
  • A. Tissi
    Tissi is a small municipality in the Sardinia region of Italy, located in the province of Sassari.
  • B. Tarmuwa
    Tarmuwa is a local government area in northeastern Nigeria known for its predominantly rural communities within Yobe State.
  • C. Takrur
    Takrur was an early West African kingdom located in the Senegal River valley, known for its role in trans-Saharan trade and its early adoption of Islam.
  • D. Anseba
    Anseba is a central region of Eritrea known for its diverse ethnic communities, agriculture, and the regional capital Keren.
  • E. Tislit
    Tislit is a small village in the Jbel Sirwa region of Morocco, known for its traditional Berber culture and mountainous surroundings.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Tun
Triple: [Hussein Onn, honorificTitle, Tun]
Generated description
Tun is the highest federal title of honor in Malaysia, bestowed by the Yang di-Pertuan Agong for extraordinary service to the nation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tun
Target entity description: Tun is the highest federal title of honor in Malaysia, bestowed by the Yang di-Pertuan Agong for extraordinary service to the nation.
  • A. Tissi
    Tissi is a small municipality in the Sardinia region of Italy, located in the province of Sassari.
  • B. Tarmuwa
    Tarmuwa is a local government area in northeastern Nigeria known for its predominantly rural communities within Yobe State.
  • C. Takrur
    Takrur was an early West African kingdom located in the Senegal River valley, known for its role in trans-Saharan trade and its early adoption of Islam.
  • D. Anseba
    Anseba is a central region of Eritrea known for its diverse ethnic communities, agriculture, and the regional capital Keren.
  • E. Tislit
    Tislit is a small village in the Jbel Sirwa region of Morocco, known for its traditional Berber culture and mountainous surroundings.
  • F. None of above. chosen

Provenance (5 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_69bd43ee52048190b81a4f066534ffb3 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64844b7081909c9d36e4b461379e completed March 20, 2026, 3:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69be10b8e7ec81908cc1ec9b94a6bee4 completed March 21, 2026, 3:30 a.m.
NEDg Description generation batch_69be1a2de8e08190b26f206434eb9502 completed March 21, 2026, 4:10 a.m.
NED2 Entity disambiguation (via description) batch_69be1a94d8b8819092f7a273cc19ebe9 completed March 21, 2026, 4:12 a.m.
Created at: March 20, 2026, 1:19 p.m.