Triple

T264761
Position Surface form Disambiguated ID Type / Status
Subject LinkedIn E5698 entity
Predicate competitor P1375 FINISHED
Object Glassdoor
Glassdoor is an online platform where employees and former employees anonymously review companies, share salary information, and browse job listings.
 E34626 NE FINISHED

How this triple was built (4 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: Glassdoor | Statement: [LinkedIn, competitor, Glassdoor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Glassdoor
Context triple: [LinkedIn, competitor, Glassdoor]
  • A. LinkedIn
    LinkedIn is a professional networking platform and social media service focused on careers, business connections, and job opportunities.
  • B. Jobs
    Jobs is the surname of Steve Jobs, the influential co-founder and longtime leader of Apple Inc.
  • C. Google
    Google is a multinational technology company best known for its search engine and wide range of internet-related products and services, including Android, YouTube, and cloud computing.
  • D. MIT Alumni Pool
    MIT Alumni Pool is an indoor swimming facility on the MIT campus that serves students, alumni, and the broader community for recreation, training, and aquatic programs.
  • E. Facebook
    Facebook is a major global social networking platform that allows users to connect, share content, and communicate online.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Glassdoor
Triple: [LinkedIn, competitor, Glassdoor]
Generated description
Glassdoor is an online platform where employees and former employees anonymously review companies, share salary information, and browse job listings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Glassdoor
Target entity description: Glassdoor is an online platform where employees and former employees anonymously review companies, share salary information, and browse job listings.
  • A. LinkedIn
    LinkedIn is a professional networking platform and social media service focused on careers, business connections, and job opportunities.
  • B. Jobs
    Jobs is the surname of Steve Jobs, the influential co-founder and longtime leader of Apple Inc.
  • C. Google
    Google is a multinational technology company best known for its search engine and wide range of internet-related products and services, including Android, YouTube, and cloud computing.
  • D. MIT Alumni Pool
    MIT Alumni Pool is an indoor swimming facility on the MIT campus that serves students, alumni, and the broader community for recreation, training, and aquatic programs.
  • E. Goole
    Goole is an inland port town in the East Riding of Yorkshire, England, known for its significant docks and role in regional maritime trade.
  • F. None of above. chosen

Provenance (5 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_69a2587daeb081909591b9d30f80a271 completed Feb. 28, 2026, 2:52 a.m.
NER Named-entity recognition batch_69a25d8f9bbc8190a13841e4de093a66 completed Feb. 28, 2026, 3:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69a389ae45648190966804664bf4f861 completed March 1, 2026, 12:34 a.m.
NEDg Description generation batch_69a38a9adf4481909300cfa1fb3129cc completed March 1, 2026, 12:38 a.m.
NED2 Entity disambiguation (via description) batch_69a38aef72808190953043b9c480fada completed March 1, 2026, 12:40 a.m.
Created at: Feb. 28, 2026, 2:56 a.m.