Triple

T14132828
Position Surface form Disambiguated ID Type / Status
Subject Brynden Tully E350210 entity
Predicate title P38 FINISHED
Object Ser
Ser is a knightly honorific used in the world of "A Song of Ice and Fire" and "Game of Thrones," equivalent to "Sir" in addressing knights.
 E1082626 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: Ser | Statement: [Brynden Tully, title, Ser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ser
Context triple: [Brynden Tully, title, Ser]
  • A. Sen
    Sen is a common Indian surname, particularly prevalent among Bengali communities and associated with numerous notable figures in academia, arts, and public life.
  • B. SER
    SER is the commonly used abbreviation for South Eastern Railway, a major railway zone in India.
  • C. Serio
    Serio is a river in northern Italy that flows through the Lombardy region and joins the Adda River.
  • D. Sher
    Sher is a surname most notably associated with American cinematographer Lawrence Sher, known for his work on films like "Joker" and "The Hangover" series.
  • E. Sus
    Sus is a genus of mammals in the pig family that includes domestic pigs and several species of wild boar.
  • 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: Ser
Triple: [Brynden Tully, title, Ser]
Generated description
Ser is a knightly honorific used in the world of "A Song of Ice and Fire" and "Game of Thrones," equivalent to "Sir" in addressing knights.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ser
Target entity description: Ser is a knightly honorific used in the world of "A Song of Ice and Fire" and "Game of Thrones," equivalent to "Sir" in addressing knights.
  • A. Sen
    Sen is a common Indian surname, particularly prevalent among Bengali communities and associated with numerous notable figures in academia, arts, and public life.
  • B. SER
    SER is the commonly used abbreviation for South Eastern Railway, a major railway zone in India.
  • C. Serio
    Serio is a river in northern Italy that flows through the Lombardy region and joins the Adda River.
  • D. Sher
    Sher is a surname most notably associated with American cinematographer Lawrence Sher, known for his work on films like "Joker" and "The Hangover" series.
  • E. Sus
    Sus is a genus of mammals in the pig family that includes domestic pigs and several species of wild boar.
  • 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_69d827865f608190b311820428ae027b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de610cece88190b4a86500677e5938 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcdf1288b48190a382732fac13aaf7 completed May 7, 2026, 6:50 p.m.
NEDg Description generation batch_69fce0dec2488190be9c24d3744e7243 completed May 7, 2026, 6:58 p.m.
NED2 Entity disambiguation (via description) batch_69fce206b0588190a0f4b24231d3c365 completed May 7, 2026, 7:03 p.m.
Created at: April 9, 2026, 11:28 p.m.