Triple

T2924067
Position Surface form Disambiguated ID Type / Status
Subject Byzantine navy E78800 entity
Predicate usedShipType P11945 FINISHED
Object dromon
A dromon was a fast, oared warship that formed the backbone of the Byzantine Empire’s Mediterranean naval forces during the Middle Ages.
E309605 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: dromon | Statement: [Byzantine navy, usedShipType, dromon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: dromon
Context triple: [Byzantine navy, usedShipType, dromon]
  • A. DRO
    DRO is the commonly used acronym for the Division of Regional Operations, an organizational unit that oversees and coordinates activities across multiple geographic regions.
  • B. Drongen
    Drongen is a district of the Belgian city of Ghent, known as a suburban area in East Flanders.
  • C. Drehu
    Drehu is an Austronesian language spoken primarily by the indigenous population of Lifou Island in New Caledonia.
  • D. Dern
    Dern is a surname most prominently associated with American actor Bruce Dern and his family of performers.
  • E. Mnajdra
    Mnajdra is an ancient megalithic temple complex on Malta’s southern coast, renowned for its prehistoric architecture and astronomical alignments.
  • 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: dromon
Triple: [Byzantine navy, usedShipType, dromon]
Generated description
A dromon was a fast, oared warship that formed the backbone of the Byzantine Empire’s Mediterranean naval forces during the Middle Ages.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: dromon
Target entity description: A dromon was a fast, oared warship that formed the backbone of the Byzantine Empire’s Mediterranean naval forces during the Middle Ages.
  • A. DRO
    DRO is the commonly used acronym for the Division of Regional Operations, an organizational unit that oversees and coordinates activities across multiple geographic regions.
  • B. Drongen
    Drongen is a district of the Belgian city of Ghent, known as a suburban area in East Flanders.
  • C. Drehu
    Drehu is an Austronesian language spoken primarily by the indigenous population of Lifou Island in New Caledonia.
  • D. Dern
    Dern is a surname most prominently associated with American actor Bruce Dern and his family of performers.
  • E. Mnajdra
    Mnajdra is an ancient megalithic temple complex on Malta’s southern coast, renowned for its prehistoric architecture and astronomical alignments.
  • 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_69ad8b0d40b481908bc2a5fa2e73c3fb completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad97bf2df88190bd4f1e90d4656507 completed March 8, 2026, 3:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69b056375b5c819081c7d4fd506cbf25 completed March 10, 2026, 5:34 p.m.
NEDg Description generation batch_69b05f640afc8190bf9b5b90ff7c9b0e completed March 10, 2026, 6:13 p.m.
NED2 Entity disambiguation (via description) batch_69b06010c1948190a2e13084a79b106b completed March 10, 2026, 6:16 p.m.
Created at: March 8, 2026, 2:55 p.m.