Triple

T37873155

Position	Surface form	Disambiguated ID	Type / Status
Subject	Hunter Rise	`E944653`	entity
Predicate	guardFaction	`P25766`	FINISHED
Object	Thunder Bluff Guards Thunder Bluff Guards are the tauren city guards responsible for maintaining order and protecting the capital of Thunder Bluff in World of Warcraft.	`E2247387`	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: Thunder Bluff Guards | Statement: [Hunter Rise, guardFaction, Thunder Bluff Guards]

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: Thunder Bluff Guards
Triple: [Hunter Rise, guardFaction, Thunder Bluff Guards]

Generated description

Thunder Bluff Guards are the tauren city guards responsible for maintaining order and protecting the capital of Thunder Bluff in World of Warcraft.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: guardFaction
Context triple: [Hunter Rise, guardFaction, Thunder Bluff Guards]

A. guard
Indicates that one entity protects, watches over, or defends another entity or resource from harm, intrusion, or unauthorized access.
B. guardRegiment
Indicates that one entity serves as a protective or security regiment for another entity.
C. garrisonSide
Indicates the side, faction, or allegiance that a garrison is associated with or belongs to.
D. guardFeature
Indicates that one entity protects, secures, or restricts access to a particular feature of another entity.
E. hasFaction chosen
Indicates that an entity is affiliated with, belongs to, or is represented by a particular faction or group.
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_69f76eef55d481908ca6660b4b532550`	completed	May 3, 2026, 3:51 p.m.
NER	Named-entity recognition	`batch_69fbc995dc2481908b3bd4217f8101e7`	completed	May 6, 2026, 11:07 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a410428ba9881909d78eef0d96bbfde`	completed	June 28, 2026, 11:23 a.m.
NEDg	Description generation	`batch_6a410508bc348190b5f53d578d31e158`	completed	June 28, 2026, 11:27 a.m.
NED2	Entity disambiguation (via description)	`batch_6a4106705f7881908428bc38ccfb838c`	completed	June 28, 2026, 11:33 a.m.
PD	Predicate disambiguation	`batch_69fbc8ee04f08190977b7ad70fc85896`	completed	May 6, 2026, 11:04 p.m.

Created at: May 3, 2026, 4:19 p.m.