Triple

T25355899

Position	Surface form	Disambiguated ID	Type / Status
Subject	Tom Leahy	`E635818`	entity
Predicate	hasNameInstance	`P164167`	FINISHED
Object	Tom Leahy (Australian footballer) Tom Leahy (Australian footballer) was an early 20th-century Australian rules footballer best known for his ruck work with North Adelaide in the South Australian Football League and for representing South Australia in interstate matches.	`E1674664`	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: Tom Leahy (Australian footballer) | Statement: [Tom Leahy, hasNameInstance, Tom Leahy (Australian footballer)]

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: Tom Leahy (Australian footballer)
Triple: [Tom Leahy, hasNameInstance, Tom Leahy (Australian footballer)]

Generated description

Tom Leahy (Australian footballer) was an early 20th-century Australian rules footballer best known for his ruck work with North Adelaide in the South Australian Football League and for representing South Australia in interstate matches.

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

Target predicate: hasNameInstance
Context triple: [Tom Leahy, hasNameInstance, Tom Leahy (Australian footballer)]

A. hasNameCharacteristic
Indicates that an entity possesses a specific quality or attribute related to its name.
B. hasNameFunction
Indicates that an entity is associated with a function whose purpose is to provide or determine its name.
C. hasNameString
Indicates that an entity is associated with a specific textual string used as its name.
D. hasNameInFamily
Indicates that an entity is known or referred to by a particular name within the context of a specific family or familial group.
E. hasNameInIAST
Indicates that an entity is associated with a specific name written in the International Alphabet of Sanskrit Transliteration (IAST) system.
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_69e75a9b7cf481909f2dcdfb37d95ca7`	completed	April 21, 2026, 11:08 a.m.
NER	Named-entity recognition	`batch_69f643c204508190a43fe0ec5165b01c`	completed	May 2, 2026, 6:34 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a1075fd4c0081908b40904f881ea3b6`	completed	May 22, 2026, 3:27 p.m.
NEDg	Description generation	`batch_6a1076ba66588190bc35f122ee016bb0`	completed	May 22, 2026, 3:31 p.m.
NED2	Entity disambiguation (via description)	`batch_6a1077935d948190b863fda3fdd47965`	completed	May 22, 2026, 3:34 p.m.
PD	Predicate disambiguation	`batch_69f641da05b881909f6283c988639c53`	completed	May 2, 2026, 6:26 p.m.
PDg	Predicate description generation	`batch_69f6430975b481909191219ad13ef77e`	completed	May 2, 2026, 6:31 p.m.

Created at: April 21, 2026, 1:36 p.m.