Triple

T27699469
Position Surface form Disambiguated ID Type / Status
Subject Lawrence G. Roberts E698388 entity
Predicate employer P7 FINISHED
Object ARPA Information Processing Techniques Office
The ARPA Information Processing Techniques Office was a pioneering U.S. government research unit within ARPA (now DARPA) that funded and directed early computer science and networking projects, including the development of ARPANET.
E1785530 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: ARPA Information Processing Techniques Office | Statement: [Lawrence G. Roberts, employer, ARPA Information Processing Techniques Office]
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: ARPA Information Processing Techniques Office
Triple: [Lawrence G. Roberts, employer, ARPA Information Processing Techniques Office]
Generated description
The ARPA Information Processing Techniques Office was a pioneering U.S. government research unit within ARPA (now DARPA) that funded and directed early computer science and networking projects, including the development of ARPANET.

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_69ef590ea74081908f0cd7500d85fa27 completed April 27, 2026, 12:39 p.m.
NER Named-entity recognition batch_69f635a1611881908cf175d623831a42 completed May 2, 2026, 5:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12e456fdb08190972cc8c2cfcdace0 completed May 24, 2026, 11:43 a.m.
NEDg Description generation batch_6a12e51506ac8190bc8cac0bad87dad5 completed May 24, 2026, 11:46 a.m.
NED2 Entity disambiguation (via description) batch_6a12e5e1eafc8190912e291b91690548 completed May 24, 2026, 11:49 a.m.
Created at: April 27, 2026, 2:56 p.m.