Triple

T19412457
Position Surface form Disambiguated ID Type / Status
Subject Eliza Helm E485622 entity
Predicate familyName P18 FINISHED
Object Helm 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: Helm | Statement: [Eliza Helm, familyName, Helm]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helm
Context triple: [Eliza Helm, familyName, Helm]
  • A. Helm
    Helm is a popular package manager for Kubernetes that simplifies defining, installing, and upgrading complex containerized applications using reusable charts.
  • B. Helm chosen
    Helm is a surname of Germanic origin borne by various notable individuals, including members of prominent American families.
  • C. Hilt
    Hilt is a dependency injection library for Android that builds on Dagger to simplify and standardize DI setup across app components.
  • D. Hengist Pod
    Hengist Pod is a timid British slave-turned-reluctant hero and inventor in the 1964 comedy film "Carry On Cleo."
  • E. Helikon
    Helikon is a mountain in Greek mythology, often associated with the Muses and poetic inspiration.
  • 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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62af77eb481909fcfb6cdde1e8580 completed April 20, 2026, 1:32 p.m.
Created at: April 10, 2026, 1:37 p.m.