Triple

T34362312
Position Surface form Disambiguated ID Type / Status
Subject Royal Marines Armoured Support Group E881909 entity
Predicate equipment P2728 FINISHED
Object Centaur IV tank
The Centaur IV tank was a British World War II cruiser tank variant, armed with a 95 mm howitzer and used primarily for close-support roles such as providing fire support during amphibious landings.
E2103201 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: Centaur IV tank | Statement: [Royal Marines Armoured Support Group, equipment, Centaur IV tank]
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: Centaur IV tank
Triple: [Royal Marines Armoured Support Group, equipment, Centaur IV tank]
Generated description
The Centaur IV tank was a British World War II cruiser tank variant, armed with a 95 mm howitzer and used primarily for close-support roles such as providing fire support during amphibious landings.

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_69f349be5c9c81908dc726ae1f4c68f2 completed April 30, 2026, 12:23 p.m.
NER Named-entity recognition batch_69f7182aacb481908edc5ceead43bb01 completed May 3, 2026, 9:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a3740f235b881908d74d88282b36915 completed June 21, 2026, 1:40 a.m.
NEDg Description generation batch_6a374189e1b881908f19247a3a1104d2 completed June 21, 2026, 1:42 a.m.
NED2 Entity disambiguation (via description) batch_6a3741f66d88819081e0566ae6ded487 completed June 21, 2026, 1:44 a.m.
Created at: May 1, 2026, 1:58 a.m.