Triple

T13664806
Position Surface form Disambiguated ID Type / Status
Subject Hebrus E327089 entity
Predicate hasNameForm P19207 FINISHED
Object Ἕβρος
Ἕβρος is the ancient Greek name for the river now known as the Maritsa, which flows through Bulgaria, Greece, and Turkey.
E1055049 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: Ἕβρος | Statement: [Hebrus, hasNameForm, Ἕβρος]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ἕβρος
Context triple: [Hebrus, hasNameForm, Ἕβρος]
  • A. Hera Limenia
    Hera Limenia is a local maritime aspect of the Greek goddess Hera, venerated as a protector of harbors and seafaring.
  • B. Nea Erythraia
    Nea Erythraia is a suburban area in the northern part of the Athens metropolitan region in Greece, known for its residential character and proximity to Kifisia.
  • C. Lemnos
    Lemnos is a Greek island in the northern Aegean Sea known for its volcanic landscape, ancient sanctuaries, and traditional villages.
  • D. Ἠχώ
    Ἠχώ is the Greek mythological nymph cursed to only repeat the words of others, from whom the modern term “echo” is derived.
  • E. Evia
    Evia is the modern Greek name for Euboea, the second-largest Greek island, located off the eastern coast of mainland Greece.
  • 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: Ἕβρος
Triple: [Hebrus, hasNameForm, Ἕβρος]
Generated description
Ἕβρος is the ancient Greek name for the river now known as the Maritsa, which flows through Bulgaria, Greece, and Turkey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ἕβρος
Target entity description: Ἕβρος is the ancient Greek name for the river now known as the Maritsa, which flows through Bulgaria, Greece, and Turkey.
  • A. Hera Limenia
    Hera Limenia is a local maritime aspect of the Greek goddess Hera, venerated as a protector of harbors and seafaring.
  • B. Nea Erythraia
    Nea Erythraia is a suburban area in the northern part of the Athens metropolitan region in Greece, known for its residential character and proximity to Kifisia.
  • C. Lemnos
    Lemnos is a Greek island in the northern Aegean Sea known for its volcanic landscape, ancient sanctuaries, and traditional villages.
  • D. Ἠχώ
    Ἠχώ is the Greek mythological nymph cursed to only repeat the words of others, from whom the modern term “echo” is derived.
  • E. Evia
    Evia is the modern Greek name for Euboea, the second-largest Greek island, located off the eastern coast of mainland Greece.
  • 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_69d8076d8270819092afc2f0e9c359a8 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc622a07c81909ef7fb55e719dd9a completed April 12, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7943bfaf0819097410e901847d77c completed May 3, 2026, 6:30 p.m.
NEDg Description generation batch_69f79655d5f08190a3cbf3e12e2ffa67 completed May 3, 2026, 6:39 p.m.
NED2 Entity disambiguation (via description) batch_69f7972a1cf48190a1d435227414967a completed May 3, 2026, 6:42 p.m.
Created at: April 9, 2026, 9:52 p.m.