Triple

T17048332
Position Surface form Disambiguated ID Type / Status
Subject Yaxhá E413627 entity
Predicate nearbySite P350 FINISHED
Object Nakum
Nakum is an ancient Maya archaeological site in northeastern Guatemala, noted for its well-preserved temples and plazas within the Yaxhá-Nakum-Naranjo National Park.
 E1247993 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: Nakum | Statement: [Yaxhá, nearbySite, Nakum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Nakum
Context triple: [Yaxhá, nearbySite, Nakum]
  • A. Naklua
    Naklua is a coastal district in the northern part of Pattaya, Thailand, known for its traditional fishing community, seafood markets, and quieter, more local atmosphere compared to central Pattaya.
  • B. Naju
    Naju is a historic city in South Korea known for its pear cultivation and location in the southwestern province of South Jeolla.
  • C. Kumait
    Kumait is a town located within Iraq’s Maysan Governorate in the southeastern part of the country.
  • D. Ukaan
    Ukaan is a little-documented Niger-Congo language spoken by a small community in southwestern Nigeria.
  • E. Nakara
    Nakara is a residential suburb in the northern part of Darwin, Northern Territory, Australia, known for its family-friendly streets and proximity to Casuarina’s major shopping and educational facilities.
  • 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: Nakum
Triple: [Yaxhá, nearbySite, Nakum]
Generated description
Nakum is an ancient Maya archaeological site in northeastern Guatemala, noted for its well-preserved temples and plazas within the Yaxhá-Nakum-Naranjo National Park.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Nakum
Target entity description: Nakum is an ancient Maya archaeological site in northeastern Guatemala, noted for its well-preserved temples and plazas within the Yaxhá-Nakum-Naranjo National Park.
  • A. Naklua
    Naklua is a coastal district in the northern part of Pattaya, Thailand, known for its traditional fishing community, seafood markets, and quieter, more local atmosphere compared to central Pattaya.
  • B. Naju
    Naju is a historic city in South Korea known for its pear cultivation and location in the southwestern province of South Jeolla.
  • C. Kumait
    Kumait is a town located within Iraq’s Maysan Governorate in the southeastern part of the country.
  • D. Ukaan
    Ukaan is a little-documented Niger-Congo language spoken by a small community in southwestern Nigeria.
  • E. Nakara
    Nakara is a residential suburb in the northern part of Darwin, Northern Territory, Australia, known for its family-friendly streets and proximity to Casuarina’s major shopping and educational facilities.
  • 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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3da9f799c8190a683ae38cd990643 completed April 18, 2026, 7:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01233fb8d88190a9a6ef6a2f19a499 completed May 11, 2026, 12:30 a.m.
NEDg Description generation batch_6a012533f9a8819096ab9b821c848dd2 completed May 11, 2026, 12:39 a.m.
NED2 Entity disambiguation (via description) batch_6a0125dead2481908a5c26bda5a7cd1f completed May 11, 2026, 12:42 a.m.
Created at: April 10, 2026, 5:34 a.m.