Triple

T25823012

Position	Surface form	Disambiguated ID	Type / Status
Subject	Directive 2004/38/EC	`E650449`	entity
Predicate	repeals	`P6257`	FINISHED
Object	Directive 90/365/EEC Directive 90/365/EEC was an EU measure granting residence rights to retired workers and self-employed persons in a member state other than their own, later replaced and consolidated by Directive 2004/38/EC.	`E1719898`	NE 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: Directive 90/365/EEC | Statement: [Directive 2004/38/EC, repeals, Directive 90/365/EEC]

NEDg Description generation gpt-5.1

Instruction

Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"

Input

Entity: Directive 90/365/EEC
Triple: [Directive 2004/38/EC, repeals, Directive 90/365/EEC]

Generated description

Directive 90/365/EEC was an EU measure granting residence rights to retired workers and self-employed persons in a member state other than their own, later replaced and consolidated by Directive 2004/38/EC.

Provenance (5 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_69e7ab367fcc8190a5ff1e7f3da046a4`	completed	April 21, 2026, 4:52 p.m.
NER	Named-entity recognition	`batch_69f60192afc881908dd64d8024d75329`	completed	May 2, 2026, 1:52 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a119a31260c8190bab0e879bb081122`	completed	May 23, 2026, 12:14 p.m.
NEDg	Description generation	`batch_6a119aa510bc819083c4e8264616f63a`	completed	May 23, 2026, 12:16 p.m.
NED2	Entity disambiguation (via description)	`batch_6a119b318d4881908d658464d8ea390c`	completed	May 23, 2026, 12:18 p.m.

Created at: April 22, 2026, 7:30 a.m.