Triple

T36296847

Position	Surface form	Disambiguated ID	Type / Status
Subject	Saint Mary above Minerva	`E893392`	entity
Predicate	hasFountainOrMonumentInFront	`P126713`	FINISHED
Object	Bernini’s elephant and obelisk Bernini’s elephant and obelisk is a 17th-century Baroque sculpture in Rome featuring an ancient Egyptian obelisk mounted on the back of a marble elephant, designed by Gian Lorenzo Bernini.	`E2176441`	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: Bernini’s elephant and obelisk | Statement: [Saint Mary above Minerva, hasFountainOrMonumentInFront, Bernini’s elephant and obelisk]

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: Bernini’s elephant and obelisk
Triple: [Saint Mary above Minerva, hasFountainOrMonumentInFront, Bernini’s elephant and obelisk]

Generated description

Bernini’s elephant and obelisk is a 17th-century Baroque sculpture in Rome featuring an ancient Egyptian obelisk mounted on the back of a marble elephant, designed by Gian Lorenzo Bernini.

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

Target predicate: hasFountainOrMonumentInFront
Context triple: [Saint Mary above Minerva, hasFountainOrMonumentInFront, Bernini’s elephant and obelisk]

A. hasPublicSquareInFront
Indicates that a building or structure has a public square located directly in front of it.
B. hasMonumentInCenter chosen
Indicates that a place or area has a monument located at its central point or main focal area.
C. isPublicMonument
Indicates that something is officially designated, accessible, and recognized as a monument in a public space.
D. hasPrimaryMonument
Indicates that an entity is associated with its main or most significant monument.
E. hasMonumentFunction
Indicates that something serves the role or purpose of a monument, such as commemorating, honoring, or symbolizing a person, event, or idea.
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_69f76e4a61f0819084a2b68dbbb4efc6`	completed	May 3, 2026, 3:48 p.m.
NER	Named-entity recognition	`batch_69fe87b609888190913b0c3f787ecdba`	completed	May 9, 2026, 1:02 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a396e256b808190944b1823c2576136`	completed	June 22, 2026, 5:17 p.m.
NEDg	Description generation	`batch_6a396ebb4224819081b9d1f60d22b488`	completed	June 22, 2026, 5:19 p.m.
NED2	Entity disambiguation (via description)	`batch_6a3970fbbc608190bf438b9446a9be3d`	completed	June 22, 2026, 5:29 p.m.
PD	Predicate disambiguation	`batch_69fe8731af48819092084f6f74bf052d`	completed	May 9, 2026, 1 a.m.

Created at: May 3, 2026, 4:09 p.m.