Triple
T17978569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cydonia |
E449539
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Pyrus |
—
|
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: Pyrus | Statement: [Cydonia, relatedTo, Pyrus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pyrus Context triple: [Cydonia, relatedTo, Pyrus]
-
A.
Pyrus
chosen
Pyrus is a genus of flowering plants best known for including the cultivated pear trees that produce edible pears.
-
B.
Pêra
Pêra is a small village in Portugal’s Algarve region, known for its traditional architecture and proximity to popular coastal and tourist areas.
-
C.
Aplu
Aplu is an Etruscan deity closely associated with the Greek god Apollo, linked to prophecy, healing, and possibly plague.
-
D.
Malus
Malus is a genus of deciduous trees and shrubs in the rose family best known for cultivated apples and ornamental crabapples.
-
E.
Naran
Naran is a popular mountain resort town and tourist destination in northern Pakistan, known for its scenic valleys, rivers, and access to sites like Lake Saif-ul-Malook.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b201d1508190a9d6abbfd04bdcae |
completed | April 19, 2026, 10:44 a.m. |
Created at: April 10, 2026, 10:22 a.m.