Triple

T23104600
Position Surface form Disambiguated ID Type / Status
Subject Dimocarpus E576125 entity
Predicate relatedTo P37 FINISHED
Object Nephelium 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: Nephelium | Statement: [Dimocarpus, relatedTo, Nephelium]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nephelium
Context triple: [Dimocarpus, relatedTo, Nephelium]
  • A. Nephelium chosen
    Nephelium is a genus of tropical trees best known for producing the rambutan and related edible fruits.
  • B. Artocarpus
    Artocarpus is a genus of tropical trees in the mulberry family that includes economically important fruit species such as breadfruit and jackfruit.
  • C. Spondias
    Spondias is a genus of tropical fruit-bearing trees known for species like hog plum and ambarella, valued for their edible, often tangy fruits.
  • D. Eriobotrya
    Eriobotrya is a genus of flowering plants in the rose family, best known for the loquat tree that produces edible, plum-like fruits.
  • E. Psidium
    Psidium is a genus of tropical and subtropical flowering plants in the myrtle family, best known for species such as the common guava that produce edible, aromatic fruits.
  • 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_69e245f4af548190898d434a64a1e774 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18deb702c819099f2e2141706f00e completed April 29, 2026, 4:49 a.m.
Created at: April 17, 2026, 3:58 p.m.