Triple

T8896126
Position Surface form Disambiguated ID Type / Status
Subject Tomis E211808 entity
Predicate greekName P3659 FINISHED
Object Τόμις
Τόμις is the ancient Greek name for the city of Tomis, a historic Black Sea port best known as the place of the Roman poet Ovid’s exile.
E765179 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: Τόμις | Statement: [Tomis, greekName, Τόμις]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Τόμις
Context triple: [Tomis, greekName, Τόμις]
  • A. Taje
    Taje is an Austronesian language spoken in Central Sulawesi, Indonesia, belonging to the Tomini–Tolitoli subgroup.
  • B. Tomia
    Tomia is an island in Indonesia’s Wakatobi archipelago, renowned for its pristine coral reefs and exceptional scuba diving and snorkeling sites.
  • C. Toliš
    Toliš is the endonym used by speakers of the Talysh language to refer to their own language or ethnic group in the Talysh region of Iran and Azerbaijan.
  • D. Tumpa
    Tumpa is a song featured on the album "Legend of the Sun Virgin."
  • E. Uma
    Uma is a central antagonist in Disney's "Descendants" franchise, known as the ambitious and strong-willed daughter of Ursula who leads a pirate crew on the Isle of the Lost.
  • 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: Τόμις
Triple: [Tomis, greekName, Τόμις]
Generated description
Τόμις is the ancient Greek name for the city of Tomis, a historic Black Sea port best known as the place of the Roman poet Ovid’s exile.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Τόμις
Target entity description: Τόμις is the ancient Greek name for the city of Tomis, a historic Black Sea port best known as the place of the Roman poet Ovid’s exile.
  • A. Taje
    Taje is an Austronesian language spoken in Central Sulawesi, Indonesia, belonging to the Tomini–Tolitoli subgroup.
  • B. Tomia
    Tomia is an island in Indonesia’s Wakatobi archipelago, renowned for its pristine coral reefs and exceptional scuba diving and snorkeling sites.
  • C. Toliš
    Toliš is the endonym used by speakers of the Talysh language to refer to their own language or ethnic group in the Talysh region of Iran and Azerbaijan.
  • D. Tumpa
    Tumpa is a song featured on the album "Legend of the Sun Virgin."
  • E. Uma
    Uma is an Austronesian language spoken primarily in Central Sulawesi, Indonesia.
  • 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_69ca83918d3081909b326fa3750cb8c8 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc61bfec0881908e4ef5b7f0e6b542 completed April 1, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfac02974881908a7e8d9cfa47e624 completed April 3, 2026, 12:01 p.m.
NEDg Description generation batch_69cfad512ad081908e046e9d95097071 completed April 3, 2026, 12:06 p.m.
NED2 Entity disambiguation (via description) batch_69cfadf4c1fc81908df957dc0a6308dc completed April 3, 2026, 12:09 p.m.
Created at: March 30, 2026, 6:54 p.m.