Triple

T16773778
Position Surface form Disambiguated ID Type / Status
Subject Tripylon E407670 entity
Predicate connects P390 FINISHED
Object Tachara
Tachara is an ancient Achaemenid palace at Persepolis, built by Darius the Great and notable for its finely carved reliefs and well-preserved stonework.
 E1234001 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: Tachara | Statement: [Tripylon, connects, Tachara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tachara
Context triple: [Tripylon, connects, Tachara]
  • A. Tarare
    Tarare is a commune in eastern France known historically for its textile industry and its location in the hilly Beaujolais region of the Rhône department.
  • B. Tahkuna
    Tahkuna is a coastal settlement in northern Estonia, located on Hiiumaa Island and known for its proximity to the historic Tahkuna Lighthouse.
  • C. Tucheim
    Tucheim is a village and former municipality that is now part of the town of Genthin in the German state of Saxony-Anhalt.
  • D. Tashir
    Tashir is a small town located in Armenia’s northern Lori Province.
  • E. Tamahú
    Tamahú is a municipality and town located in the Alta Verapaz Department of central Guatemala, known for its highland landscapes and predominantly indigenous Maya population.
  • 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: Tachara
Triple: [Tripylon, connects, Tachara]
Generated description
Tachara is an ancient Achaemenid palace at Persepolis, built by Darius the Great and notable for its finely carved reliefs and well-preserved stonework.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tachara
Target entity description: Tachara is an ancient Achaemenid palace at Persepolis, built by Darius the Great and notable for its finely carved reliefs and well-preserved stonework.
  • A. Tarare
    Tarare is a commune in eastern France known historically for its textile industry and its location in the hilly Beaujolais region of the Rhône department.
  • B. Tahkuna
    Tahkuna is a coastal settlement in northern Estonia, located on Hiiumaa Island and known for its proximity to the historic Tahkuna Lighthouse.
  • C. Tucheim
    Tucheim is a village and former municipality that is now part of the town of Genthin in the German state of Saxony-Anhalt.
  • D. Tashir
    Tashir is a small town located in Armenia’s northern Lori Province.
  • E. Tamahú
    Tamahú is a municipality and town located in the Alta Verapaz Department of central Guatemala, known for its highland landscapes and predominantly indigenous Maya population.
  • 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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b037c5708190ba604e7707b5a8a2 completed April 18, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00aafc28c0819084ecd6e5be6adec9 completed May 10, 2026, 3:57 p.m.
NEDg Description generation batch_6a00abfe035881909330d356bb497229 completed May 10, 2026, 4:02 p.m.
NED2 Entity disambiguation (via description) batch_6a00ac54a11c81909afe9244e9fe0656 completed May 10, 2026, 4:03 p.m.
Created at: April 10, 2026, 5:21 a.m.