Triple
T36274757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unshu mikan |
E892773
|
entity |
| Predicate | hasPeelCharacteristic |
P138846
|
FINISHED |
| Object | easy to peel |
—
|
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: easy to peel | Statement: [Unshu mikan, hasPeelCharacteristic, easy to peel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPeelCharacteristic Context triple: [Unshu mikan, hasPeelCharacteristic, easy to peel]
-
A.
hasPeelType
chosen
Indicates the type or characteristic of the outer peel or skin associated with an entity.
-
B.
peelColor
Indicates the color of an entity’s outer peel or skin surface.
-
C.
peelUsedAs
Indicates that an outer layer or skin (a peel) is utilized or repurposed for some function, product, or process.
-
D.
hasHumanCharacteristic
Indicates that an entity possesses a trait, quality, or behavior typically associated with humans.
-
E.
hasFillingCharacteristic
Indicates that something possesses a particular quality, property, or attribute related to its filling.
- 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_69f76e488f34819083e254dbe288c27a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe610e1f6881908f10070ba64643cf |
completed | May 8, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69fe604c6c008190ad659e9b9fa82f7b |
completed | May 8, 2026, 10:14 p.m. |
Created at: May 3, 2026, 4:09 p.m.