Triple

T15583300
Position Surface form Disambiguated ID Type / Status
Subject Agron E374552 entity
Predicate capital P234 FINISHED
Object Rhizon
Rhizon was an ancient Illyrian city that served as a significant political and economic center on the eastern Adriatic coast.
 E1165645 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: Rhizon | Statement: [Agron, capital, Rhizon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rhizon
Context triple: [Agron, capital, Rhizon]
  • A. Rairok
    Rairok is a small islet and community area within the Marshall Islands' capital atoll of Majuro.
  • B. Zonaras
    Zonaras was a 12th-century Byzantine chronicler and former imperial official best known for his Epitome of Histories, a major source for earlier lost works on Roman and Byzantine history.
  • C. Hyele
    Hyele is the ancient name of the coastal town of Velia in southern Italy, historically associated with the Greek colony of Elea in Magna Graecia.
  • D. Rineia
    Rineia is a small, uninhabited Greek island in the Aegean Sea, lying next to Delos and administratively part of the Cyclades archipelago.
  • E. Viadrus
    Viadrus is the ancient Latin name historically used to refer to the Oder River in Central Europe.
  • 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: Rhizon
Triple: [Agron, capital, Rhizon]
Generated description
Rhizon was an ancient Illyrian city that served as a significant political and economic center on the eastern Adriatic coast.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rhizon
Target entity description: Rhizon was an ancient Illyrian city that served as a significant political and economic center on the eastern Adriatic coast.
  • A. Rairok
    Rairok is a small islet and community area within the Marshall Islands' capital atoll of Majuro.
  • B. Zonaras
    Zonaras was a 12th-century Byzantine chronicler and former imperial official best known for his Epitome of Histories, a major source for earlier lost works on Roman and Byzantine history.
  • C. Hyele
    Hyele is the ancient name of the coastal town of Velia in southern Italy, historically associated with the Greek colony of Elea in Magna Graecia.
  • D. Rineia
    Rineia is a small, uninhabited Greek island in the Aegean Sea, lying next to Delos and administratively part of the Cyclades archipelago.
  • E. Viadrus
    Viadrus is the ancient Latin name historically used to refer to the Oder River in Central Europe.
  • 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_69d85ccd575081908909b71a3f3e3a61 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e47971481909e986dd999354628 completed April 16, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c4f71e48190a15eb0a2138f083f completed May 9, 2026, 3:01 p.m.
NEDg Description generation batch_69ff4fb2522481909fa66c2e1fac23bf completed May 9, 2026, 3:16 p.m.
NED2 Entity disambiguation (via description) batch_69ff5238f0e88190b280942022480c12 completed May 9, 2026, 3:26 p.m.
Created at: April 10, 2026, 4:11 a.m.