Triple

T8395065
Position Surface form Disambiguated ID Type / Status
Subject Mordred E198032 entity
Predicate nameVariant P744 FINISHED
Object Modred
Modred is an alternative spelling of Mordred, the treacherous knight of Arthurian legend who ultimately brings about King Arthur’s downfall.
E731008 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: Modred | Statement: [Mordred, nameVariant, Modred]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Modred
Context triple: [Mordred, nameVariant, Modred]
  • A. Hruodhaid
    Hruodhaid was a daughter of Charlemagne, the Frankish king and first Holy Roman Emperor, and a member of the Carolingian royal family in the 8th–9th century.
  • B. Fergus Mór
    Fergus Mór was a legendary early medieval king traditionally credited with founding the Scottish kingdom of Dál Riata and helping establish the Gaelic presence in western Scotland.
  • C. Godric
    Godric is a 1980 historical novel by Frederick Buechner that fictionalizes the life and spiritual journey of the medieval English saint Godric of Finchale.
  • D. Moclan
    Moclan are a fictional, predominantly male, rigidly traditional alien species from the science fiction TV series "The Orville."
  • E. Amlaíb
    Amlaíb is a medieval Gaelic form of the Norse name Olaf, commonly associated with Viking rulers in Ireland and Scotland.
  • 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: Modred
Triple: [Mordred, nameVariant, Modred]
Generated description
Modred is an alternative spelling of Mordred, the treacherous knight of Arthurian legend who ultimately brings about King Arthur’s downfall.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Modred
Target entity description: Modred is an alternative spelling of Mordred, the treacherous knight of Arthurian legend who ultimately brings about King Arthur’s downfall.
  • A. Hruodhaid
    Hruodhaid was a daughter of Charlemagne, the Frankish king and first Holy Roman Emperor, and a member of the Carolingian royal family in the 8th–9th century.
  • B. Fergus Mór
    Fergus Mór was a legendary early medieval king traditionally credited with founding the Scottish kingdom of Dál Riata and helping establish the Gaelic presence in western Scotland.
  • C. Godric
    Godric is a 1980 historical novel by Frederick Buechner that fictionalizes the life and spiritual journey of the medieval English saint Godric of Finchale.
  • D. Moclan
    Moclan are a fictional, predominantly male, rigidly traditional alien species from the science fiction TV series "The Orville."
  • E. Amlaíb
    Amlaíb is a medieval Gaelic form of the Norse name Olaf, commonly associated with Viking rulers in Ireland and Scotland.
  • 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_69ca82f816bc8190ab321c07d72208c1 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb81874d6c8190bbc0ac832d8a339d completed March 31, 2026, 8:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde85ee7b08190bfbcbed0edb142dd completed April 2, 2026, 3:54 a.m.
NEDg Description generation batch_69cdebfc63e8819087f5c1d588b58e21 completed April 2, 2026, 4:09 a.m.
NED2 Entity disambiguation (via description) batch_69cded77618c81909e8786ccd2f3e4b6 completed April 2, 2026, 4:15 a.m.
Created at: March 30, 2026, 6:03 p.m.