Triple

T5882519
Position Surface form Disambiguated ID Type / Status
Subject Ladin orthography E130781 entity
Predicate isUsedFor P98 FINISHED
Object Ladin media
Ladin media comprises newspapers, radio, television, and digital outlets that publish and broadcast content in the Ladin language, helping preserve and promote this Rhaeto-Romance minority tongue.
E553054 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: Ladin media | Statement: [Ladin orthography, isUsedFor, Ladin media]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ladin media
Context triple: [Ladin orthography, isUsedFor, Ladin media]
  • A. Ladurlad
    Ladurlad is a central heroic figure in Robert Southey's epic poem "The Curse of Kehama," known for enduring a supernatural curse that renders him sleepless and invulnerable.
  • B. Ladania
    Ladania is a town located in the Madhubani district of the Indian state of Bihar.
  • C. LJ
    LJ is the third-generation model of the Holden Torana, a compact Australian car produced in the early 1970s and known for its performance-oriented variants.
  • D. Latada
    Latada is a traditional student festival at the University of Coimbra, marked by parades, music, and academic rituals celebrating the start of the academic year.
  • E. LBN
    LBN is the three-letter ISO 3166-1 alpha-3 country code for Lebanon.
  • 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: Ladin media
Triple: [Ladin orthography, isUsedFor, Ladin media]
Generated description
Ladin media comprises newspapers, radio, television, and digital outlets that publish and broadcast content in the Ladin language, helping preserve and promote this Rhaeto-Romance minority tongue.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ladin media
Target entity description: Ladin media comprises newspapers, radio, television, and digital outlets that publish and broadcast content in the Ladin language, helping preserve and promote this Rhaeto-Romance minority tongue.
  • A. Ladurlad
    Ladurlad is a central heroic figure in Robert Southey's epic poem "The Curse of Kehama," known for enduring a supernatural curse that renders him sleepless and invulnerable.
  • B. Ladania
    Ladania is a town located in the Madhubani district of the Indian state of Bihar.
  • C. LJ
    LJ is the third-generation model of the Holden Torana, a compact Australian car produced in the early 1970s and known for its performance-oriented variants.
  • D. Latada
    Latada is a traditional student festival at the University of Coimbra, marked by parades, music, and academic rituals celebrating the start of the academic year.
  • E. LBN
    LBN is the three-letter ISO 3166-1 alpha-3 country code for Lebanon.
  • 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_69c0085628dc8190b334c1b44c067efc completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c03673ecd88190978993056b675259 completed March 22, 2026, 6:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0b13330c88190b10f33843f10f51f completed March 23, 2026, 3:19 a.m.
NEDg Description generation batch_69c0b2442bf881908aeaecb46463e32d completed March 23, 2026, 3:23 a.m.
NED2 Entity disambiguation (via description) batch_69c0b2bc8b9c8190ab642d317056b1de completed March 23, 2026, 3:25 a.m.
Created at: March 22, 2026, 3:57 p.m.