Triple

T25456855

Position	Surface form	Disambiguated ID	Type / Status
Subject	Venetian patriciate	`E637935`	entity
Predicate	membershipRecordedIn	`P126378`	FINISHED
Object	Libro d’Oro The Libro d’Oro was the official register of Venice’s hereditary nobility, listing the families entitled to belong to the city’s ruling patriciate.	`E1681258`	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: Libro d’Oro | Statement: [Venetian patriciate, membershipRecordedIn, Libro d’Oro]

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: Libro d’Oro
Triple: [Venetian patriciate, membershipRecordedIn, Libro d’Oro]

Generated description

The Libro d’Oro was the official register of Venice’s hereditary nobility, listing the families entitled to belong to the city’s ruling patriciate.

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

Target predicate: membershipRecordedIn
Context triple: [Venetian patriciate, membershipRecordedIn, Libro d’Oro]

A. membershipRecordedBy
Indicates that the recording or documentation of a membership was carried out or created by a specific agent or system.
B. membershipIn
Indicates that an entity belongs to, is part of, or holds membership in a particular group, organization, or collection.
C. membershipPublishedIn chosen
Indicates that a membership or affiliation is formally recorded or made public within a specific publication or published source.
D. membershipBy
Indicates that one entity holds membership or belongs to a group, organization, or collection defined by another entity.
E. clubMembership
Indicates that an entity belongs to, is enrolled in, or holds membership status within a particular club.
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_69e75db8bab08190baca80b4a8c315fd`	completed	April 21, 2026, 11:21 a.m.
NER	Named-entity recognition	`batch_69f6691f5e188190b12c7b2eb729a45e`	completed	May 2, 2026, 9:14 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a1089b29dc88190b22aae8b224368a5`	completed	May 22, 2026, 4:52 p.m.
NEDg	Description generation	`batch_6a108a88dd5c8190ac1f024420860c32`	completed	May 22, 2026, 4:55 p.m.
NED2	Entity disambiguation (via description)	`batch_6a108b266a648190874a4e80f1df2bb8`	completed	May 22, 2026, 4:58 p.m.
PD	Predicate disambiguation	`batch_69f66598d6008190a7ca8ff80399fd34`	completed	May 2, 2026, 8:59 p.m.

Created at: April 21, 2026, 2:10 p.m.