Triple

T11008437
Position Surface form Disambiguated ID Type / Status
Subject Tibetan Empire E260180 entity
Predicate ruler P403 FINISHED
Object Langdarma
Langdarma was a 9th-century Tibetan king known for his persecution of Buddhism and for presiding over the collapse of the Tibetan Empire.
 E899353 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: Langdarma | Statement: [Tibetan Empire, ruler, Langdarma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Langdarma
Context triple: [Tibetan Empire, ruler, Langdarma]
  • A. Thoosa
    Thoosa is a minor sea nymph in Greek mythology, known primarily as the mother of the Cyclops Polyphemus by the sea god Poseidon.
  • B. Mahates
    Mahates is a municipality and town in northern Colombia known for its Afro-Colombian cultural heritage and historical significance in the Bolívar Department.
  • C. Daymian
    Daymian is a masculine given name, typically considered a modern spelling variant of Damian.
  • D. Akurgal
    Akurgal is a Turkish surname most notably associated with the prominent archaeologist Ekrem Akurgal.
  • E. Dorohusk
    Dorohusk is a village in eastern Poland near the Ukrainian border, known as an important road and rail border crossing point between the two countries.
  • 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: Langdarma
Triple: [Tibetan Empire, ruler, Langdarma]
Generated description
Langdarma was a 9th-century Tibetan king known for his persecution of Buddhism and for presiding over the collapse of the Tibetan Empire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Langdarma
Target entity description: Langdarma was a 9th-century Tibetan king known for his persecution of Buddhism and for presiding over the collapse of the Tibetan Empire.
  • A. Thoosa
    Thoosa is a minor sea nymph in Greek mythology, known primarily as the mother of the Cyclops Polyphemus by the sea god Poseidon.
  • B. Mahates
    Mahates is a municipality and town in northern Colombia known for its Afro-Colombian cultural heritage and historical significance in the Bolívar Department.
  • C. Daymian
    Daymian is a masculine given name, typically considered a modern spelling variant of Damian.
  • D. Akurgal
    Akurgal is a Turkish surname most notably associated with the prominent archaeologist Ekrem Akurgal.
  • E. Dorohusk
    Dorohusk is a village in eastern Poland near the Ukrainian border, known as an important road and rail border crossing point between the two countries.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7978810208190b8e2966ae67b6314 completed April 9, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69e37498b9fc8190860acede4f49ea4a completed April 18, 2026, 12:10 p.m.
NEDg Description generation batch_69e378dcc92c8190952d4acfee2a309c completed April 18, 2026, 12:28 p.m.
NED2 Entity disambiguation (via description) batch_69e37be75a588190abb9569ef1e87279 completed April 18, 2026, 12:41 p.m.
Created at: April 8, 2026, 9:25 p.m.