Triple

T3017763
Position Surface form Disambiguated ID Type / Status
Subject Lost Horizon E82377 entity
Predicate character P662 FINISHED
Object High Lama
High Lama is the wise and enigmatic spiritual leader of the hidden utopian lamasery of Shangri-La in James Hilton’s novel "Lost Horizon."
E319631 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: High Lama | Statement: [Lost Horizon, character, High Lama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: High Lama
Context triple: [Lost Horizon, character, High Lama]
  • A. Ang Lhamu
    Ang Lhamu was the wife of famed Sherpa mountaineer Tenzing Norgay, who helped make history with the first confirmed ascent of Mount Everest.
  • B. Tamang
    Tamang is a Sino-Tibetan language spoken primarily by the Tamang people of Nepal and the Nepali diaspora, including Nepali Americans.
  • C. Hoch
    Hoch is the nickname of Ed Hochuli, a well-known former NFL referee recognized for his muscular physique and detailed penalty explanations.
  • D. Gwarinpa
    Gwarinpa is a large, planned residential district in Abuja, Nigeria, known for its extensive housing estates and relatively well-organized urban layout.
  • E. Tusita Heaven
    Tusita Heaven is a celestial realm in Buddhist cosmology where future Buddhas, including Maitreya, dwell before their final rebirth and enlightenment.
  • 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: High Lama
Triple: [Lost Horizon, character, High Lama]
Generated description
High Lama is the wise and enigmatic spiritual leader of the hidden utopian lamasery of Shangri-La in James Hilton’s novel "Lost Horizon."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: High Lama
Target entity description: High Lama is the wise and enigmatic spiritual leader of the hidden utopian lamasery of Shangri-La in James Hilton’s novel "Lost Horizon."
  • A. Ang Lhamu
    Ang Lhamu was the wife of famed Sherpa mountaineer Tenzing Norgay, who helped make history with the first confirmed ascent of Mount Everest.
  • B. Tamang
    Tamang is a Sino-Tibetan language spoken primarily by the Tamang people of Nepal and the Nepali diaspora, including Nepali Americans.
  • C. Hoch
    Hoch is the nickname of Ed Hochuli, a well-known former NFL referee recognized for his muscular physique and detailed penalty explanations.
  • D. Gwarinpa
    Gwarinpa is a large, planned residential district in Abuja, Nigeria, known for its extensive housing estates and relatively well-organized urban layout.
  • E. Tusita Heaven
    Tusita Heaven is a celestial realm in Buddhist cosmology where future Buddhas, including Maitreya, dwell before their final rebirth and enlightenment.
  • 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_69ad8b1eb53481908c39bbcd1ec104b2 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9a90ea64819080620e60bbd6aa24 completed March 8, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b12e71a9c08190848ecb3bcab18bb5 completed March 11, 2026, 8:57 a.m.
NEDg Description generation batch_69b132319fd481908426670f319f56c5 completed March 11, 2026, 9:13 a.m.
NED2 Entity disambiguation (via description) batch_69b1d6729f848190a275638f074c1729 completed March 11, 2026, 8:54 p.m.
Created at: March 8, 2026, 3 p.m.