Triple

T35644584

Position	Surface form	Disambiguated ID	Type / Status
Subject	RAF Luqa	`E1029971`	entity
Predicate	hostedUnit	`P3556`	FINISHED
Object	No. 37 Squadron RAF No. 37 Squadron RAF was a Royal Air Force unit best known for its long-range bomber and later maritime patrol operations, particularly during the World Wars and the early Cold War era.	`E2288009`	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: No. 37 Squadron RAF | Statement: [RAF Luqa, hostedUnit, No. 37 Squadron RAF]

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: No. 37 Squadron RAF
Triple: [RAF Luqa, hostedUnit, No. 37 Squadron RAF]

Generated description

No. 37 Squadron RAF was a Royal Air Force unit best known for its long-range bomber and later maritime patrol operations, particularly during the World Wars and the early Cold War era.

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_69f76e087bdc8190a4794bf9c0bd7634`	completed	May 3, 2026, 3:47 p.m.
NER	Named-entity recognition	`batch_69f79f4ecd7481909b39e84120c16a45`	completed	May 3, 2026, 7:17 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a5a5ad1cf488190bb2e70306892bb3e`	completed	July 17, 2026, 4:39 p.m.
NEDg	Description generation	`batch_6a5a5b5b11b08190b56754ee3c918272`	completed	July 17, 2026, 4:42 p.m.
NED2	Entity disambiguation (via description)	`batch_6a5a5baee3ec8190bd079436e0d2d9ad`	completed	July 17, 2026, 4:43 p.m.

Created at: May 3, 2026, 4:05 p.m.