Triple

T25093152
Position Surface form Disambiguated ID Type / Status
Subject Dilip Mehta E628517 entity
Predicate notableWork P4 FINISHED
Object The Forgotten Woman
The Forgotten Woman is a documentary film by Dilip Mehta that explores the lives and struggles of widows in India who are marginalized and abandoned by society.
 E1662538 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: The Forgotten Woman | Statement: [Dilip Mehta, notableWork, The Forgotten Woman]
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: The Forgotten Woman
Triple: [Dilip Mehta, notableWork, The Forgotten Woman]
Generated description
The Forgotten Woman is a documentary film by Dilip Mehta that explores the lives and struggles of widows in India who are marginalized and abandoned by society.

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_69e2ff2f58e881908340527bc5d34f07 completed April 18, 2026, 3:49 a.m.
NER Named-entity recognition batch_69f464b691bc81908e0a286c32a902e8 completed May 1, 2026, 8:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1048ea21148190b688671c8d8aff35 completed May 22, 2026, 12:15 p.m.
NEDg Description generation batch_6a104a2a89e08190aa35e97ffb57fc9a completed May 22, 2026, 12:20 p.m.
NED2 Entity disambiguation (via description) batch_6a104bc667e48190bb0feadc5b324cde completed May 22, 2026, 12:27 p.m.
Created at: April 18, 2026, 6:24 a.m.