Triple

T25277972
Position Surface form Disambiguated ID Type / Status
Subject Orson Krennic E633750 entity
Predicate vehicle P7735 FINISHED
Object Delta-class T-3c shuttle
The Delta-class T-3c shuttle is an angular, heavily modified Imperial transport used by Director Orson Krennic in the Star Wars universe, notable for its folding wings and imposing, stealthy design.
E1677790 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: Delta-class T-3c shuttle | Statement: [Orson Krennic, vehicle, Delta-class T-3c shuttle]
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: Delta-class T-3c shuttle
Triple: [Orson Krennic, vehicle, Delta-class T-3c shuttle]
Generated description
The Delta-class T-3c shuttle is an angular, heavily modified Imperial transport used by Director Orson Krennic in the Star Wars universe, notable for its folding wings and imposing, stealthy design.

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_69e75a9402fc81909362ca85277c06d9 completed April 21, 2026, 11:08 a.m.
NER Named-entity recognition batch_69f48ba8e99081908b3fd911e8634dcc completed May 1, 2026, 11:16 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1075d72c4c81909197a5b6dd8025b2 completed May 22, 2026, 3:27 p.m.
NEDg Description generation batch_6a1079fb77c081909db1dd37ea17bd25 completed May 22, 2026, 3:44 p.m.
NED2 Entity disambiguation (via description) batch_6a107a847e648190a71ba78b0a3a70ee completed May 22, 2026, 3:47 p.m.
Created at: April 21, 2026, 1:18 p.m.