Triple

T14780354
Position Surface form Disambiguated ID Type / Status
Subject Grey Worm E347373 entity
Predicate culture P1114 FINISHED
Object Unsullied E343672 NE FINISHED

How this triple was built (2 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: Unsullied | Statement: [Grey Worm, culture, Unsullied]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Unsullied
Context triple: [Grey Worm, culture, Unsullied]
  • A. Unsullied chosen
    The Unsullied are elite, eunuch slave-soldiers renowned for their discipline, fearlessness, and combat prowess in the world of "A Song of Ice and Fire" and its TV adaptation "Game of Thrones."
  • B. Kingsguard
    The Kingsguard is an elite order of sworn knights in the world of Westeros tasked with protecting the ruling monarch and royal family, bound by vows of lifelong service and celibacy.
  • C. Nymeria
    Nymeria is Arya Stark’s fierce direwolf companion in the world of Game of Thrones/A Song of Ice and Fire.
  • D. Brienne of Tarth
    Brienne of Tarth is a formidable and honor-bound warrior noblewoman from the A Song of Ice and Fire novels and the Game of Thrones television series.
  • E. Princess Nymeria
    Princess Nymeria is a legendary Rhoynar ruler famed for leading her people across the sea to settle in Dorne and forging a powerful alliance that reshaped its history.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deca9c7cac8190ba900df95e42e318 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe388d398c81909d275f487cc38d9c completed May 8, 2026, 7:25 p.m.
Created at: April 10, 2026, 1:31 a.m.