Triple
T11658803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ender Dragon |
E277072
|
entity |
| Predicate | spawnsOn |
P18866
|
FINISHED |
| Object | obsidian pillars in the End |
—
|
LITERAL 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: obsidian pillars in the End | Statement: [Ender Dragon, spawnsOn, obsidian pillars in the End]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spawnsOn Context triple: [Ender Dragon, spawnsOn, obsidian pillars in the End]
-
A.
spawningLocation
chosen
Indicates the place or environment where an entity originates, appears, or is generated.
-
B.
livesOn
Indicates that one entity resides or has its home on or atop another entity (such as a surface, structure, or geographic feature).
-
C.
growsOn
Indicates that one entity develops or increases in size, number, or extent while being physically supported by or attached to another entity.
-
D.
locatedOnTerrain
Indicates that one entity is physically situated on or atop a particular terrain surface.
-
E.
simulatesHabitatOf
Indicates that one entity artificially recreates or models the living conditions or environment characteristic of another entity’s natural habitat.
- 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_69d6aafbb3c081908a9cdb4ecb8d981d |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a3d19c788190826d849a6ffedc72 |
completed | April 10, 2026, 7:16 a.m. |
| PD | Predicate disambiguation | batch_69d85ddc780481909a3bc63832fe2bd2 |
completed | April 10, 2026, 2:18 a.m. |
Created at: April 8, 2026, 9:39 p.m.