Triple

T32225728
Position Surface form Disambiguated ID Type / Status
Subject Tod Andrews E823193 entity
Predicate notableWork P4 FINISHED
Object The Gray Ghost
The Gray Ghost is a 1950s American television series dramatizing the exploits of Confederate cavalry officer John Singleton Mosby during the U.S. Civil War.
 E557491 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 Gray Ghost | Statement: [Tod Andrews, notableWork, The Gray Ghost]
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 Gray Ghost
Triple: [Tod Andrews, notableWork, The Gray Ghost]
Generated description
The Gray Ghost is a 1950s American television series dramatizing the exploits of Confederate cavalry officer John Singleton Mosby during the U.S. Civil War.

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_69f3490b4f948190b99e4f999f5be25f completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f6bbcb07ec81909e1d6c7eb24fbdd7 completed May 3, 2026, 3:06 a.m.
NED1 Entity disambiguation (via context triple) batch_6a2f3ba55240819089cf2081defcdec1 completed June 14, 2026, 11:39 p.m.
NEDg Description generation batch_6a2f3c6228388190ac68cfbe4aa06306 completed June 14, 2026, 11:42 p.m.
NED2 Entity disambiguation (via description) batch_6a2f40454f3c81908fbc6be995ff5c07 completed June 14, 2026, 11:59 p.m.
Created at: May 1, 2026, 12:38 a.m.