Triple

T37539215
Position Surface form Disambiguated ID Type / Status
Subject Sethekk Halls E933282 entity
Predicate contains P35 FINISHED
Object Sethekk Prophet
Sethekk Prophet is a bird-like arakkoa spellcaster mini-boss found within the Sethekk Halls dungeon in World of Warcraft.
E2281358 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: Sethekk Prophet | Statement: [Sethekk Halls, contains, Sethekk Prophet]
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: Sethekk Prophet
Triple: [Sethekk Halls, contains, Sethekk Prophet]
Generated description
Sethekk Prophet is a bird-like arakkoa spellcaster mini-boss found within the Sethekk Halls dungeon in World of Warcraft.

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_69f76ec999288190ae26ec7b6aea7046 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fba41e52a08190b416c3750ed77764 completed May 6, 2026, 8:27 p.m.
NED1 Entity disambiguation (via context triple) batch_6a4205a4f4208190b5a0dbb0b7dcbd89 completed June 29, 2026, 5:41 a.m.
NEDg Description generation batch_6a42075fef0c8190a251675803cae81e completed June 29, 2026, 5:49 a.m.
NED2 Entity disambiguation (via description) batch_6a4207cf118c8190a87b64cbcb7bdfc9 completed June 29, 2026, 5:51 a.m.
Created at: May 3, 2026, 4:17 p.m.