Triple

T24386559

Position	Surface form	Disambiguated ID	Type / Status
Subject	Cliffs of Moher	`E614764`	entity
Predicate	OBrienTowerBuiltBy	`P156009`	FINISHED
Object	Cornelius O'Brien Cornelius O'Brien was a 19th-century Irish Member of Parliament and local landlord known for developing the Cliffs of Moher area as a tourist destination.	`E1644634`	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: Cornelius O'Brien | Statement: [Cliffs of Moher, OBrienTowerBuiltBy, Cornelius O'Brien]

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: Cornelius O'Brien
Triple: [Cliffs of Moher, OBrienTowerBuiltBy, Cornelius O'Brien]

Generated description

Cornelius O'Brien was a 19th-century Irish Member of Parliament and local landlord known for developing the Cliffs of Moher area as a tourist destination.

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

Target predicate: OBrienTowerBuiltBy
Context triple: [Cliffs of Moher, OBrienTowerBuiltBy, Cornelius O'Brien]

A. architectOfMainBuilding
Indicates that one entity is the architect who designed the main building associated with another entity.
B. NassauHallCompleted
Indicates that the construction of Nassau Hall has been finished or brought to completion.
C. foundingBuilding
Indicates that a particular building is the original or primary structure where an organization, institution, or entity was founded.
D. timeballTowerBuilt
Indicates that a time ball tower was constructed or built at a certain time or by a certain agent.
E. builtStructureFor
Indicates that one entity constructed or assembled a structure specifically intended for the use, benefit, or purpose of another entity.
F. None of above. chosen

Provenance (7 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_69e2d7e362e481909e32fe4ef8269d4f`	completed	April 18, 2026, 1:01 a.m.
NER	Named-entity recognition	`batch_69f29454c36c8190b7820dbf5af7b695`	completed	April 29, 2026, 11:29 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a10045f75bc81908f0d96e7c48fc484`	completed	May 22, 2026, 7:23 a.m.
NEDg	Description generation	`batch_6a10078172348190af481658252dedee`	completed	May 22, 2026, 7:36 a.m.
NED2	Entity disambiguation (via description)	`batch_6a10083cf1508190bd1bb8441d93c735`	completed	May 22, 2026, 7:39 a.m.
PD	Predicate disambiguation	`batch_69f287c4a2b48190b80fb7a3c0e9b018`	completed	April 29, 2026, 10:35 p.m.
PDg	Predicate description generation	`batch_69f28f4d978c81908310c01def2514cc`	completed	April 29, 2026, 11:07 p.m.

Created at: April 18, 2026, 2:03 a.m.