Triple

T35906936

Position	Surface form	Disambiguated ID	Type / Status
Subject	Jane Pierce	`E1038497`	entity
Predicate	delegateDutiesTo	`P96404`	FINISHED
Object	Abigail Kent Means (her aunt) for White House hostess duties Abigail Kent Means was the aunt of First Lady Jane Pierce who stepped in to perform White House hostess responsibilities during Pierce’s tenure.	`E2160832`	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: Abigail Kent Means (her aunt) for White House hostess duties | Statement: [Jane Pierce, delegateDutiesTo, Abigail Kent Means (her aunt) for White House hostess duties]

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: Abigail Kent Means (her aunt) for White House hostess duties
Triple: [Jane Pierce, delegateDutiesTo, Abigail Kent Means (her aunt) for White House hostess duties]

Generated description

Abigail Kent Means was the aunt of First Lady Jane Pierce who stepped in to perform White House hostess responsibilities during Pierce’s tenure.

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

Target predicate: delegateDutiesTo
Context triple: [Jane Pierce, delegateDutiesTo, Abigail Kent Means (her aunt) for White House hostess duties]

A. assumesDutiesOf
Indicates that one entity takes over and begins performing the responsibilities or role previously held by another entity.
B. delegateCan
Indicates that one entity has the authority or ability to transfer certain responsibilities, powers, or tasks to another entity.
C. delegationTitle
Indicates the official role or title associated with a particular delegation relationship between entities.
D. entrustedTo chosen
Indicates that responsibility, care, or control of something has been formally given by one party to another.
E. shiftedAuthorityTo
Indicates that decision-making power or control has been transferred from one entity to another.
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_69f76e2259608190bf6788a132e0d139`	completed	May 3, 2026, 3:47 p.m.
NER	Named-entity recognition	`batch_69f7aa6fd79c8190b1a70068ace78068`	completed	May 3, 2026, 8:05 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a38ae297d2c8190adbec34ef206cc9a`	completed	June 22, 2026, 3:38 a.m.
NEDg	Description generation	`batch_6a38ae942ddc8190b125685dbf7407e2`	completed	June 22, 2026, 3:40 a.m.
NED2	Entity disambiguation (via description)	`batch_6a38af0c461c8190a7332d1709b5553c`	completed	June 22, 2026, 3:42 a.m.
PD	Predicate disambiguation	`batch_69f7a8d435288190b30b1991fb003121`	completed	May 3, 2026, 7:58 p.m.

Created at: May 3, 2026, 4:07 p.m.