Triple
T37470102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zereth Mortis |
E931131
|
entity |
| Predicate | hasSubZone |
P747
|
FINISHED |
| Object |
Haven
Haven is a central refuge and quest hub in World of Warcraft’s Zereth Mortis zone, serving as the primary base of operations for players exploring the realm of the First Ones.
|
E2229557
|
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: Haven | Statement: [Zereth Mortis, hasSubZone, Haven]
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: Haven Triple: [Zereth Mortis, hasSubZone, Haven]
Generated description
Haven is a central refuge and quest hub in World of Warcraft’s Zereth Mortis zone, serving as the primary base of operations for players exploring the realm of the First Ones.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubZone Context triple: [Zereth Mortis, hasSubZone, Haven]
-
A.
hasZone
Indicates that one entity possesses, contains, or is associated with a specific zone or designated area.
-
B.
hasSubrealm
Indicates that one realm or domain is a subordinate or contained sub-part of another, higher-level realm or domain.
-
C.
hasSubdivision
chosen
Indicates that one entity is divided into and contains another entity as one of its constituent parts or administrative units.
-
D.
hasZoneStructure
Indicates that an entity possesses a defined internal division into zones or regions, each forming part of its overall structure.
-
E.
hasSuburbanZone
Indicates that an entity includes or is associated with a suburban area within its spatial or administrative extent.
- 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_69f76ec2af148190897d101070d7f415 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a004fd3caf48190b2ec063a7bf0756b |
completed | May 10, 2026, 9:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a4095298c1081909c4b06adf42fd0c5 |
completed | June 28, 2026, 3:29 a.m. |
| NEDg | Description generation | batch_6a4095fe8f0081908a1f18ec3a865393 |
completed | June 28, 2026, 3:33 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a40966fc7288190993e424e2c2d088a |
completed | June 28, 2026, 3:35 a.m. |
| PD | Predicate disambiguation | batch_6a004f7672dc8190aca91d1ed855bf9a |
completed | May 10, 2026, 9:27 a.m. |
Created at: May 3, 2026, 4:17 p.m.