Triple

T19940660
Position Surface form Disambiguated ID Type / Status
Subject Λυκία E479298 entity
Predicate hasMajorCity P316 FINISHED
Object Τλη
Τλη was an ancient city of Lycia in southwestern Anatolia, known from classical sources as one of the region’s notable urban centers.
 E1403418 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: Τλη | Statement: [Λυκία, hasMajorCity, Τλη]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Τλη
Context triple: [Λυκία, hasMajorCity, Τλη]
  • A. Tule
    Tule are an Indigenous people of Panama and Colombia, also known as the Guna or Kuna, recognized for their autonomous island communities and vibrant textile art called molas.
  • B. Tsioti
    Tsioti is the former name of the town now known as Farkadona in central Greece.
  • C. Λητώ
    Λητώ is the Greek name for Leto, a Titaness in Greek mythology best known as the mother of the Olympian twins Apollo and Artemis.
  • D. Teliu
    Teliu is a commune in Brașov County, Romania, known for its scenic location in the historical region of Țara Bârsei (Burzenland) in Transylvania.
  • E. Telu
    Telu is the ISO 15924 four-letter code that represents the Telugu script used for writing the Telugu language and several other South Asian languages.
  • 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: Τλη
Triple: [Λυκία, hasMajorCity, Τλη]
Generated description
Τλη was an ancient city of Lycia in southwestern Anatolia, known from classical sources as one of the region’s notable urban centers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Τλη
Target entity description: Τλη was an ancient city of Lycia in southwestern Anatolia, known from classical sources as one of the region’s notable urban centers.
  • A. Tule
    Tule are an Indigenous people of Panama and Colombia, also known as the Guna or Kuna, recognized for their autonomous island communities and vibrant textile art called molas.
  • B. Tsioti
    Tsioti is the former name of the town now known as Farkadona in central Greece.
  • C. Λητώ
    Λητώ is the Greek name for Leto, a Titaness in Greek mythology best known as the mother of the Olympian twins Apollo and Artemis.
  • D. Teliu
    Teliu is a commune in Brașov County, Romania, known for its scenic location in the historical region of Țara Bârsei (Burzenland) in Transylvania.
  • E. Telu
    Telu is the ISO 15924 four-letter code that represents the Telugu script used for writing the Telugu language and several other South Asian languages.
  • 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a1a8df4819094e84855465df6c0 completed April 20, 2026, 4:53 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07f6eebbb0819087108b2c76e15af1 completed May 16, 2026, 4:47 a.m.
NEDg Description generation batch_6a07f79a4e5081908b92f3268f43fe5a completed May 16, 2026, 4:50 a.m.
NED2 Entity disambiguation (via description) batch_6a07f813ea288190825eebcc1bf705b3 completed May 16, 2026, 4:52 a.m.
Created at: April 10, 2026, 1:53 p.m.