Triple

T7231843
Position Surface form Disambiguated ID Type / Status
Subject Form I-9 E154920 entity
Predicate listAPurpose P75912 FINISHED
Object establish both identity and employment authorization 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: establish both identity and employment authorization | Statement: [Form I-9, listAPurpose, establish both identity and employment authorization]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: listAPurpose
Context triple: [Form I-9, listAPurpose, establish both identity and employment authorization]
  • A. listsMeans
    Indicates that one entity enumerates or specifies the meaning, definition, or interpretation of another entity.
  • B. listsGiant
    Indicates that one entity enumerates or catalogs another entity that is characterized as a giant.
  • C. listType
    Indicates that one entity specifies the classification or category type of a list associated with another entity.
  • D. listsSecurity
    Indicates that an entity specifies or enumerates security-related items, settings, or attributes associated with another entity.
  • E. listedWith
    Indicates that an entity is included as an item or entry within a particular list, catalog, or collection.
  • F. None of above. chosen

Provenance (4 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_69c68811dd1c8190ac460bb39e64e1f0 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ea552a688190a00f5d0ad982f787 completed March 27, 2026, 8:36 p.m.
PD Predicate disambiguation batch_69c6e7644648819096a5e2de5d0dbe97 completed March 27, 2026, 8:24 p.m.
PDg Predicate description generation batch_69c6ea539f5c81908001524149903559 completed March 27, 2026, 8:36 p.m.
Created at: March 27, 2026, 2:54 p.m.