Triple

T29987764

Position	Surface form	Disambiguated ID	Type / Status
Subject	Heinen’s Downtown Cleveland (Cleveland Trust Rotunda)	`E761776`	entity
Predicate	formerOccupantOfBuilding	`P7727`	FINISHED
Object	Cleveland Trust Company Cleveland Trust Company was a prominent Cleveland-based banking institution that played a major role in the city’s financial and architectural history.	`E1895591`	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: Cleveland Trust Company | Statement: [Heinen’s Downtown Cleveland (Cleveland Trust Rotunda), formerOccupantOfBuilding, Cleveland Trust Company]

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: Cleveland Trust Company
Triple: [Heinen’s Downtown Cleveland (Cleveland Trust Rotunda), formerOccupantOfBuilding, Cleveland Trust Company]

Generated description

Cleveland Trust Company was a prominent Cleveland-based banking institution that played a major role in the city’s financial and architectural history.

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

Target predicate: formerOccupantOfBuilding
Context triple: [Heinen’s Downtown Cleveland (Cleveland Trust Rotunda), formerOccupantOfBuilding, Cleveland Trust Company]

A. formerOccupant chosen
Indicates that an entity previously occupied a position, role, or place but no longer does so.
B. laterOccupant
Indicates that one entity occupied or held a position in a place or role after another entity had previously done so.
C. occupiesFormerBuilding
Indicates that one entity is currently using or located in a building that was previously used or occupied by another entity.
D. formerResidenceOf
Indicates that a location was once the place where a person or entity lived or was based, but is no longer their current residence.
E. occupiesFormerEstateOf
Indicates that one entity currently resides in, uses, or controls a property that was previously the estate of another entity.
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_69f2246851148190b8e76206db94b105`	completed	April 29, 2026, 3:31 p.m.
NER	Named-entity recognition	`batch_69fec25f0fc48190b87ab1f9cd1eb0de`	completed	May 9, 2026, 5:13 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a272201cc208190ae849ffb0d80aec3`	completed	June 8, 2026, 8:11 p.m.
NEDg	Description generation	`batch_6a2724257ad88190aa9148edaeb01096`	completed	June 8, 2026, 8:20 p.m.
NED2	Entity disambiguation (via description)	`batch_6a272738fe988190ba8b43c819546bb4`	completed	June 8, 2026, 8:34 p.m.
PD	Predicate disambiguation	`batch_69fec079a770819098df7cc3049df954`	completed	May 9, 2026, 5:04 a.m.

Created at: April 29, 2026, 6:37 p.m.