Triple
T37662631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potion of Healing |
E937749
|
entity |
| Predicate | lingeringBrewedWith |
P162782
|
FINISHED |
| Object | dragon's breath |
—
|
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: dragon's breath | Statement: [Potion of Healing, lingeringBrewedWith, dragon's breath]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lingeringBrewedWith Context triple: [Potion of Healing, lingeringBrewedWith, dragon's breath]
-
A.
brewedUsing
chosen
Indicates that one entity was produced or prepared by using another entity as an ingredient, material, or component in a brewing process.
-
B.
brewedAccordingTo
Indicates that something has been produced or prepared following a specified brewing method, recipe, or standard.
-
C.
brewedAt
Indicates that a beverage or batch was produced or brewed at a specific location or facility.
-
D.
requiresBrewingKnowledgeOf
Indicates that performing or understanding the subject action or entity depends on having knowledge or expertise in brewing.
-
E.
hasCaffeineContent
Indicates that one entity (typically a beverage or substance) possesses a specified amount or presence of caffeine.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbb084760c8190a1554985d3c3cb7a |
completed | May 6, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69fbadf3cb548190ba3b7514f76b790a |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:18 p.m.