Triple

T16035539
Position Surface form Disambiguated ID Type / Status
Subject Tehanu E388960 entity
Predicate focusesOn P31 FINISHED
Object a traumatized child named Therru
Therru is a deeply scarred, withdrawn young girl in Ursula K. Le Guin’s Earthsea cycle whose past abuse and mysterious inner power make her central to the later novels’ exploration of trauma and healing.
E1190622 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: a traumatized child named Therru | Statement: [Tehanu, focusesOn, a traumatized child named Therru]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: a traumatized child named Therru
Context triple: [Tehanu, focusesOn, a traumatized child named Therru]
  • A. Threst
    Threst is a minor character appearing in the Doctor Who serial "Attack of the Cybermen."
  • B. Thurio
    Thurio is a foolish and cowardly nobleman in Shakespeare’s comedy "The Two Gentlemen of Verona," presented as an unworthy suitor to Silvia.
  • C. Thel
    Thel is a shortened given name or nickname derived from the name Thelma.
  • D. Torey
    Torey is a given name, typically used as a variant of names like Tore or Tory.
  • E. Terri
    Terri is a supporting character in the comedy film "Beauty Shop," contributing to the ensemble of stylists and clients at the salon.
  • 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: a traumatized child named Therru
Triple: [Tehanu, focusesOn, a traumatized child named Therru]
Generated description
Therru is a deeply scarred, withdrawn young girl in Ursula K. Le Guin’s Earthsea cycle whose past abuse and mysterious inner power make her central to the later novels’ exploration of trauma and healing.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: a traumatized child named Therru
Target entity description: Therru is a deeply scarred, withdrawn young girl in Ursula K. Le Guin’s Earthsea cycle whose past abuse and mysterious inner power make her central to the later novels’ exploration of trauma and healing.
  • A. Threst
    Threst is a minor character appearing in the Doctor Who serial "Attack of the Cybermen."
  • B. Thurio
    Thurio is a foolish and cowardly nobleman in Shakespeare’s comedy "The Two Gentlemen of Verona," presented as an unworthy suitor to Silvia.
  • C. Thel
    Thel is a shortened given name or nickname derived from the name Thelma.
  • D. Torey
    Torey is a given name, typically used as a variant of names like Tore or Tory.
  • E. Terri
    Terri is a common diminutive form of the given name Theresa.
  • 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_69d86dada3808190825d5f80d72fbe88 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1833b84608190887dafda5d081dc0 completed April 17, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbd3a1248190ad055892cebde5f0 completed May 10, 2026, 1:13 a.m.
NEDg Description generation batch_69ffdc5fd30c8190aaf66482f24285b4 completed May 10, 2026, 1:16 a.m.
NED2 Entity disambiguation (via description) batch_69ffdd0392e08190af42a0cdc5dd4c1f completed May 10, 2026, 1:18 a.m.
Created at: April 10, 2026, 4:56 a.m.