Triple

T36009585

Position	Surface form	Disambiguated ID	Type / Status
Subject	UAP building	`E1041367`	entity
Predicate	formerNameOfOccupant	`P65`	FINISHED
Object	Union des Assurances de Paris Union des Assurances de Paris was a major French insurance company that became one of the country’s leading insurers before merging into AXA in the 1990s.	`E2165199`	NE FINISHED

How this triple was built (3 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: Union des Assurances de Paris | Statement: [UAP building, formerNameOfOccupant, Union des Assurances de Paris]

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: Union des Assurances de Paris
Triple: [UAP building, formerNameOfOccupant, Union des Assurances de Paris]

Generated description

Union des Assurances de Paris was a major French insurance company that became one of the country’s leading insurers before merging into AXA in the 1990s.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: formerNameOfOccupant
Context triple: [UAP building, formerNameOfOccupant, Union des Assurances de Paris]

A. formerOccupant
Indicates that an entity previously occupied a position, role, or place but no longer does so.
B. formerlyKnownForOccupant
Indicates that an entity was previously known for having a particular occupant, but that association is no longer current.
C. tenantFormerName
Indicates that the specified name was previously used by the tenant before their current official name.
D. formerName chosen
Indicates that an entity was previously known by a different name in the past.
E. formerMemberName
Indicates that the referenced name belongs to an entity that was previously a member of a particular group, organization, or body but is no longer one.
F. None of above.

Provenance (6 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_69f76e2a02208190aedd1f9025a8b300`	completed	May 3, 2026, 3:47 p.m.
NER	Named-entity recognition	`batch_6a008098e5dc8190b7ccad8bab780343`	completed	May 10, 2026, 12:56 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a38bff7cf80819095eaafd6aa7cbc7a`	completed	June 22, 2026, 4:54 a.m.
NEDg	Description generation	`batch_6a38c0a93ce881908c7f774b519e5247`	completed	June 22, 2026, 4:57 a.m.
NED2	Entity disambiguation (via description)	`batch_6a38c14a3b6c81908d6bcb4ed8316a28`	completed	June 22, 2026, 4:59 a.m.
PD	Predicate disambiguation	`batch_6a008037267c8190990225a6ff0b3694`	completed	May 10, 2026, 12:55 p.m.

Created at: May 3, 2026, 4:07 p.m.