Triple

T11222282
Position Surface form Disambiguated ID Type / Status
Subject Campeche E265598 entity
Predicate contains P35 FINISHED
Object Edzná
Edzná is an ancient Maya archaeological site in the Mexican state of Campeche, known for its impressive pyramids, plazas, and sophisticated hydraulic systems.
 E912161 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: Edzná | Statement: [Campeche, contains, Edzná]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Edzná
Context triple: [Campeche, contains, Edzná]
  • A. Noznisky
    Noznisky is a relatively uncommon family surname associated with individuals such as Shirley Marlin Noznisky.
  • B. Zedka
    Zedka is a fellow patient in Paulo Coelho’s novel "Veronika Decides to Die," known for her struggle with depression and her role in challenging Veronika’s understanding of madness and freedom.
  • C. Eza’r
    Eza’r is the endonym used by the Chichimeca Jonaz people for their own indigenous community and language in Mexico.
  • D. Zedde
    Zedde is a small settlement located in the Dutch municipality of Waterland in the province of North Holland.
  • E. Zemba
    Zemba is a Bantu language variety spoken primarily in southwestern Angola and northern Namibia, closely related to and often considered a dialect of Herero.
  • 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: Edzná
Triple: [Campeche, contains, Edzná]
Generated description
Edzná is an ancient Maya archaeological site in the Mexican state of Campeche, known for its impressive pyramids, plazas, and sophisticated hydraulic systems.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Edzná
Target entity description: Edzná is an ancient Maya archaeological site in the Mexican state of Campeche, known for its impressive pyramids, plazas, and sophisticated hydraulic systems.
  • A. Noznisky
    Noznisky is a relatively uncommon family surname associated with individuals such as Shirley Marlin Noznisky.
  • B. Zedka
    Zedka is a fellow patient in Paulo Coelho’s novel "Veronika Decides to Die," known for her struggle with depression and her role in challenging Veronika’s understanding of madness and freedom.
  • C. Eza’r
    Eza’r is the endonym used by the Chichimeca Jonaz people for their own indigenous community and language in Mexico.
  • D. Zedde
    Zedde is a small settlement located in the Dutch municipality of Waterland in the province of North Holland.
  • E. Zemba
    Zemba is a Bantu language variety spoken primarily in southwestern Angola and northern Namibia, closely related to and often considered a dialect of Herero.
  • 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_69d6aac59460819089b9848b27f57848 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8ec8fb08190b27144ab65f85957 completed April 9, 2026, 5:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4977cab4481909c6b94ca07cd5e4a completed April 19, 2026, 8:51 a.m.
NEDg Description generation batch_69e49d38c2488190bfd4ba7772f534fe completed April 19, 2026, 9:15 a.m.
NED2 Entity disambiguation (via description) batch_69e49e8dc4ec81908d0defe77827d197 completed April 19, 2026, 9:21 a.m.
Created at: April 8, 2026, 9:30 p.m.