Triple

T27728773
Position Surface form Disambiguated ID Type / Status
Subject Board of Directors of LinkedIn E697373 entity
Predicate hasCommittee P1396 FINISHED
Object audit committee of LinkedIn
The audit committee of LinkedIn is a specialized oversight body within the company’s board of directors responsible for monitoring financial reporting, internal controls, and compliance with relevant accounting and regulatory standards.
 E1787185 NE FINISHED

How this triple was built (2 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: audit committee of LinkedIn | Statement: [Board of Directors of LinkedIn, hasCommittee, audit committee of LinkedIn]
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: audit committee of LinkedIn
Triple: [Board of Directors of LinkedIn, hasCommittee, audit committee of LinkedIn]
Generated description
The audit committee of LinkedIn is a specialized oversight body within the company’s board of directors responsible for monitoring financial reporting, internal controls, and compliance with relevant accounting and regulatory standards.

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_69ef590c3e288190ad54d2465af8ca4e completed April 27, 2026, 12:39 p.m.
NER Named-entity recognition batch_69f6364280d481909407a4104b535894 completed May 2, 2026, 5:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12e46f9994819083079e17bf0b28fb completed May 24, 2026, 11:43 a.m.
NEDg Description generation batch_6a12e5ee8f048190b98a89d0023e1eba completed May 24, 2026, 11:50 a.m.
NED2 Entity disambiguation (via description) batch_6a12e695c82c81908646433dbbe85bfc completed May 24, 2026, 11:52 a.m.
Created at: April 27, 2026, 3:10 p.m.