Triple

T16891040
Position Surface form Disambiguated ID Type / Status
Subject Adıyaman Province E424170 entity
Predicate contains P35 FINISHED
Object Arsameia
Arsameia is an ancient Greco-Persian archaeological site in southeastern Turkey, known for its rock reliefs and inscriptions linked to the Commagene Kingdom.
E1238356 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: Arsameia | Statement: [Adıyaman Province, contains, Arsameia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arsameia
Context triple: [Adıyaman Province, contains, Arsameia]
  • A. Amaseia
    Amaseia was an ancient city in northern Anatolia that served as the early capital of the Kingdom of Pontus and an important regional political and cultural center.
  • B. Tigranocerta
    Tigranocerta was an ancient Armenian royal city founded by King Tigranes the Great, notable as a major political and cultural center in the 1st century BCE.
  • C. Cameia
    Cameia is a small town in eastern Angola’s Moxico Province, known as a gateway to the nearby Cameia National Park.
  • D. Characene
    Characene was an ancient kingdom and important trading state located in the northern Persian Gulf region, centered around the city of Charax Spasinu.
  • E. Belshunu
    Belshunu was a Persian official who served as satrap (governor) of Babylonia during the Achaemenid Empire.
  • 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: Arsameia
Triple: [Adıyaman Province, contains, Arsameia]
Generated description
Arsameia is an ancient Greco-Persian archaeological site in southeastern Turkey, known for its rock reliefs and inscriptions linked to the Commagene Kingdom.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Arsameia
Target entity description: Arsameia is an ancient Greco-Persian archaeological site in southeastern Turkey, known for its rock reliefs and inscriptions linked to the Commagene Kingdom.
  • A. Amaseia
    Amaseia was an ancient city in northern Anatolia that served as the early capital of the Kingdom of Pontus and an important regional political and cultural center.
  • B. Tigranocerta
    Tigranocerta was an ancient Armenian royal city founded by King Tigranes the Great, notable as a major political and cultural center in the 1st century BCE.
  • C. Cameia
    Cameia is a small town in eastern Angola’s Moxico Province, known as a gateway to the nearby Cameia National Park.
  • D. Characene
    Characene was an ancient kingdom and important trading state located in the northern Persian Gulf region, centered around the city of Charax Spasinu.
  • E. Belshunu
    Belshunu was a Persian official who served as satrap (governor) of Babylonia during the Achaemenid Empire.
  • 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3bbc473d4819090cfea374ef5ca49 completed April 18, 2026, 5:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c2c1eee48190bc906e658d7729a4 completed May 10, 2026, 5:39 p.m.
NEDg Description generation batch_6a00c3b4a36c8190804b8616958002fc completed May 10, 2026, 5:43 p.m.
NED2 Entity disambiguation (via description) batch_6a00c434d8f88190a71c1c4c8e475e33 completed May 10, 2026, 5:45 p.m.
Created at: April 10, 2026, 5:29 a.m.