Triple

T35280335
Position Surface form Disambiguated ID Type / Status
Subject Osha E1018917 entity
Predicate firstSeenInEpisode P16444 FINISHED
Object “Cripples, Bastards, and Broken Things”
“Cripples, Bastards, and Broken Things” is the fourth episode of the first season of the television series Game of Thrones, focusing on marginalized characters and deepening the political intrigue in Westeros.
 E2133470 NE FINISHED

How this triple was built (3 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: “Cripples, Bastards, and Broken Things” | Statement: [Osha, firstSeenInEpisode, “Cripples, Bastards, and Broken Things”]
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: “Cripples, Bastards, and Broken Things”
Triple: [Osha, firstSeenInEpisode, “Cripples, Bastards, and Broken Things”]
Generated description
“Cripples, Bastards, and Broken Things” is the fourth episode of the first season of the television series Game of Thrones, focusing on marginalized characters and deepening the political intrigue in Westeros.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: firstSeenInEpisode
Context triple: [Osha, firstSeenInEpisode, “Cripples, Bastards, and Broken Things”]
  • A. firstAppearanceEpisode chosen
    Indicates the specific episode in which an entity (such as a character or item) is shown or mentioned for the first time.
  • B. firstAppearanceEpisodeNumber
    Indicates the episode number in which an entity (such as a character or item) first appears.
  • C. firstMentionedInSeries
    Indicates the work, episode, or installment in a series where a given entity is introduced or appears for the first time.
  • D. firstEpisode
    Indicates that one entity is the initial or earliest episode in the series or sequence associated with another entity.
  • E. firstUsedInSeason
    Indicates the season in which something (such as a character, item, or concept) was first introduced or used.
  • F. None of above.

Provenance (6 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_69f76de6d39c8190bb11342e4b91ff2b completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_6a037c8c34f88190ace26f555827f23e completed May 12, 2026, 7:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a380fc1146c8190a05baba52431a2c1 completed June 21, 2026, 4:22 p.m.
NEDg Description generation batch_6a38103cb2f88190ba2ca16db97ff04e completed June 21, 2026, 4:24 p.m.
NED2 Entity disambiguation (via description) batch_6a3811c18dbc8190936d4078136c12db completed June 21, 2026, 4:30 p.m.
PD Predicate disambiguation batch_6a037a0324d08190ac5b610cc0f6a38c completed May 12, 2026, 7:05 p.m.
Created at: May 3, 2026, 4:03 p.m.