Triple
T38590630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gridania |
E932443
|
entity |
| Predicate | hasAetherytePlaza |
P13926
|
FINISHED |
| Object | Gridania Aetheryte Plaza |
—
|
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: Gridania Aetheryte Plaza | Statement: [Gridania, hasAetherytePlaza, Gridania Aetheryte Plaza]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAetherytePlaza Context triple: [Gridania, hasAetherytePlaza, Gridania Aetheryte Plaza]
-
A.
hasPlaza
chosen
Indicates that an entity includes, contains, or is associated with a plaza as part of its structure or grounds.
-
B.
hasPlazaAbove
Indicates that one entity has a plaza located directly above it in a vertical or structural sense.
-
C.
hasAdjacentPlaza
Indicates that one place or structure is directly next to or bordering a plaza.
-
D.
hasAltarLocation
Indicates that an altar is situated at or associated with a specific location.
-
E.
hasTriconchSanctuary
Indicates that an entity includes or is characterized by a sanctuary space designed in a triconch (three-apsed) architectural form.
- F. None of above.
Provenance (3 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_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.