Triple
T30121490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Piranga |
E765572
|
entity |
| Predicate | wasPreviouslyClassifiedIn |
P120323
|
FINISHED |
| Object | Thraupidae |
—
|
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: Thraupidae | Statement: [Piranga, wasPreviouslyClassifiedIn, Thraupidae]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasPreviouslyClassifiedIn Context triple: [Piranga, wasPreviouslyClassifiedIn, Thraupidae]
-
A.
wasFormerlyClassifiedAs
chosen
Indicates that an entity previously belonged to a particular class or category but no longer does so.
-
B.
areClassifiedBy
Indicates that entities are assigned to one or more categories, types, or classes according to a specified classification scheme.
-
C.
isClassifiedUnder
Indicates that one entity is categorized or grouped within a broader class, type, or category represented by another entity.
-
D.
isSometimesClassifiedAs
Indicates that an entity is occasionally, but not consistently or universally, categorized under a particular type or class.
-
E.
previousClassification
Indicates that one classification precedes another in time or in an ordered sequence of classifications.
- 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_69f2247716748190ae4f16998f49ddf1 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67deb0888819090b6d69cd598c34c |
completed | May 2, 2026, 10:42 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:13 p.m.