Triple
T1155306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ray Tomlinson |
E23769
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Bolt Beranek and Newman |
E188
|
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: Bolt Beranek and Newman | Statement: [Ray Tomlinson, employer, Bolt Beranek and Newman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bolt Beranek and Newman Context triple: [Ray Tomlinson, employer, Bolt Beranek and Newman]
-
A.
Bolt Beranek and Newman
chosen
Bolt Beranek and Newman was a pioneering American research and engineering firm best known for its foundational role in developing the ARPANET, a precursor to the modern internet.
-
B.
Sloan
Sloan is a surname most notably associated with Alfred P. Sloan, the influential long-time president and chairman of General Motors.
-
C.
Postel
Postel is a surname most prominently associated with Jon Postel, a pioneering computer scientist and key architect of the early Internet.
-
D.
Otis
Otis is a globally recognized manufacturer of elevators, escalators, and moving walkways, known for pioneering vertical transportation technologies.
-
E.
Otis
Otis is a small rural town in western Massachusetts known for its forests, lakes, and outdoor recreation.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a493f0d32c8190ac74bad3c87f2641 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bc912300819084c9c69783055a70 |
completed | March 1, 2026, 10:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac5eb81790819087016b1620353417 |
completed | March 7, 2026, 5:22 p.m. |
Created at: March 1, 2026, 7:44 p.m.