Triple

T37508654
Position Surface form Disambiguated ID Type / Status
Subject Soulrender Dormazain E932160 entity
Predicate usesMechanic P23573 FINISHED
Object Agonizing Spike
Agonizing Spike is a raid boss ability in World of Warcraft that inflicts severe, sustained damage and pressure on players during the Soulrender Dormazain encounter.
E2230391 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: Agonizing Spike | Statement: [Soulrender Dormazain, usesMechanic, Agonizing Spike]
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: Agonizing Spike
Triple: [Soulrender Dormazain, usesMechanic, Agonizing Spike]
Generated description
Agonizing Spike is a raid boss ability in World of Warcraft that inflicts severe, sustained damage and pressure on players during the Soulrender Dormazain encounter.

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_69f76ec5268481909ea01c73aeeefd42 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fba3a8daac8190af1a2df9a0a85f13 completed May 6, 2026, 8:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a409536fb2081909e12a2251dc09373 completed June 28, 2026, 3:29 a.m.
NEDg Description generation batch_6a4095d447388190b220f838d899ce61 completed June 28, 2026, 3:32 a.m.
NED2 Entity disambiguation (via description) batch_6a40965a4a9881909930cd6dc75e1892 completed June 28, 2026, 3:34 a.m.
Created at: May 3, 2026, 4:17 p.m.