Triple
T38590520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hydaelyn |
E932441
|
entity |
| Predicate | hasExpansionSetting |
P194795
|
FINISHED |
| Object | Heavensward |
—
|
NE NERFINISHED |
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: Heavensward | Statement: [Hydaelyn, hasExpansionSetting, Heavensward]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExpansionSetting Context triple: [Hydaelyn, hasExpansionSetting, Heavensward]
-
A.
hasExpansion
Indicates that one entity serves as a larger, extended, or elaborated form of another entity.
-
B.
hasExpansionType
Indicates that an entity is associated with a particular mode or category of expansion (such as how it grows, extends, or scales).
-
C.
hasExpansionModel
Indicates that one entity is associated with a specific model or schema used to define how it can be expanded, detailed, or elaborated.
-
D.
hasExpansionInterface
Indicates that an entity provides or supports an interface through which it can be expanded or extended with additional components or functionality.
-
E.
hasExpansionKeyword
Indicates that an entity is associated with a keyword used to expand or broaden search, query, or matching criteria.
- F. None of above. chosen
Provenance (4 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd864235b481908738dbb69556bc62 |
completed | May 8, 2026, 6:44 a.m. |
| PD | Predicate disambiguation | batch_69fd8373b6bc819091c554f29ee17fec |
completed | May 8, 2026, 6:32 a.m. |
| PDg | Predicate description generation | batch_69fd8640e1d4819081c98f15eeb221ab |
completed | May 8, 2026, 6:44 a.m. |
Created at: May 3, 2026, 4:32 p.m.