Triple

T11445697
Position Surface form Disambiguated ID Type / Status
Subject Legio IV Flavia Felix E271257 entity
Predicate garrison P75 FINISHED
Object Burnum
Burnum was an ancient Roman military camp and settlement in the province of Dalmatia, strategically located in what is now Croatia.
 E926355 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: Burnum | Statement: [Legio IV Flavia Felix, garrison, Burnum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Burnum
Context triple: [Legio IV Flavia Felix, garrison, Burnum]
  • A. Iceburgh
    Iceburgh is the costumed penguin mascot of the NHL’s Pittsburgh Penguins, known for entertaining fans at games and team events.
  • B. Brennen
    Brennen is a given name, typically used as a variant spelling of Brennan.
  • C. Shedgum
    Shedgum is a major production area within Saudi Arabia’s vast Ghawar oil field, known for its significant contribution to the country’s crude oil output.
  • D. Taghmon
    Taghmon is a village in County Wexford, Ireland, known for its historic ecclesiastical roots and rural community character.
  • E. Buron
    Buron is a small village in northwestern France, historically notable for fighting during the Battle of Normandy in World War II.
  • 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: Burnum
Triple: [Legio IV Flavia Felix, garrison, Burnum]
Generated description
Burnum was an ancient Roman military camp and settlement in the province of Dalmatia, strategically located in what is now Croatia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Burnum
Target entity description: Burnum was an ancient Roman military camp and settlement in the province of Dalmatia, strategically located in what is now Croatia.
  • A. Iceburgh
    Iceburgh is the costumed penguin mascot of the NHL’s Pittsburgh Penguins, known for entertaining fans at games and team events.
  • B. Brennen
    Brennen is a given name, typically used as a variant spelling of Brennan.
  • C. Shedgum
    Shedgum is a major production area within Saudi Arabia’s vast Ghawar oil field, known for its significant contribution to the country’s crude oil output.
  • D. Taghmon
    Taghmon is a village in County Wexford, Ireland, known for its historic ecclesiastical roots and rural community character.
  • E. Buron
    Buron is a small village in northwestern France, historically notable for fighting during the Battle of Normandy in World War II.
  • 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_69d6aadff8888190a13f253f0d460874 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8088a66f48190b2b4a56cd62097cf completed April 9, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5d3afe7fc8190acc8c803ff5efe5a completed April 20, 2026, 7:20 a.m.
NEDg Description generation batch_69e5d5cac9108190b7756329bfa320d3 completed April 20, 2026, 7:29 a.m.
NED2 Entity disambiguation (via description) batch_69e5d7fd235081909870476cbc9817b2 completed April 20, 2026, 7:38 a.m.
Created at: April 8, 2026, 9:35 p.m.