Triple

T23671933
Position Surface form Disambiguated ID Type / Status
Subject Fiat A.12 E584753 entity
Predicate usedInAircraft P10706 FINISHED
Object Caproni Ca.4
The Caproni Ca.4 was a large Italian World War I-era heavy bomber triplane designed for long-range strategic bombing missions.
E1609349 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: Caproni Ca.4 | Statement: [Fiat A.12, usedInAircraft, Caproni Ca.4]
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: Caproni Ca.4
Triple: [Fiat A.12, usedInAircraft, Caproni Ca.4]
Generated description
The Caproni Ca.4 was a large Italian World War I-era heavy bomber triplane designed for long-range strategic bombing missions.

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_69e24901421881908c17a5293bdd4a8e completed April 17, 2026, 2:51 p.m.
NER Named-entity recognition batch_69f1b41002f881908cd744ed44b70f5d completed April 29, 2026, 7:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f75fbb81c8190b6c553604023f439 completed May 21, 2026, 9:15 p.m.
NEDg Description generation batch_6a0f76f167d08190a9e4d3abc3cc4545 completed May 21, 2026, 9:19 p.m.
NED2 Entity disambiguation (via description) batch_6a0f78c456dc8190869c04d4a5c00ceb completed May 21, 2026, 9:27 p.m.
Created at: April 17, 2026, 6:50 p.m.