Triple

T37936256

Position	Surface form	Disambiguated ID	Type / Status
Subject	2018 Polish winter K2 expedition	`E946357`	entity
Predicate	rescuedClimber	`P189809`	FINISHED
Object	Élisabeth Revol Élisabeth Revol is a French high-altitude mountaineer known for her bold winter ascents in the Himalayas and her dramatic 2018 rescue on Nanga Parbat.	`E2287617`	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: Élisabeth Revol | Statement: [2018 Polish winter K2 expedition, rescuedClimber, Élisabeth Revol]

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: Élisabeth Revol
Triple: [2018 Polish winter K2 expedition, rescuedClimber, Élisabeth Revol]

Generated description

Élisabeth Revol is a French high-altitude mountaineer known for her bold winter ascents in the Himalayas and her dramatic 2018 rescue on Nanga Parbat.

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

Target predicate: rescuedClimber
Context triple: [2018 Polish winter K2 expedition, rescuedClimber, Élisabeth Revol]

A. climber
Indicates that an entity engages in the activity of climbing, typically ascending surfaces or structures using physical effort.
B. includedClimber
Indicates that a climber is part of, or counted within, a specified group, set, or collection of climbers.
C. leadClimber
Indicates that one climber is acting as the primary or front climber responsible for leading a climbing route relative to another entity or context.
D. crewRescued
Indicates that a crew has been successfully saved from danger or a threatening situation.
E. attemptedFirstAscentOf
Indicates that an entity made an effort to be the first to successfully climb or reach the summit of a particular route, peak, or feature.
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_69f76ef531ac8190ae6d99e5786e76ec`	completed	May 3, 2026, 3:51 p.m.
NER	Named-entity recognition	`batch_69fbca6c066c8190a1599202f341417f`	completed	May 6, 2026, 11:10 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a59fff23ab4819086a927e83730b621`	completed	July 17, 2026, 10:12 a.m.
NEDg	Description generation	`batch_6a5a006063388190803f3435652a8988`	completed	July 17, 2026, 10:13 a.m.
NED2	Entity disambiguation (via description)	`batch_6a5a00bd617481908c1bfe999714ea55`	completed	July 17, 2026, 10:15 a.m.
PD	Predicate disambiguation	`batch_69fbc8ee04f08190977b7ad70fc85896`	completed	May 6, 2026, 11:04 p.m.
PDg	Predicate description generation	`batch_69fbc993caa881908c16c3e21efaeef9`	completed	May 6, 2026, 11:07 p.m.

Created at: May 3, 2026, 4:20 p.m.