Triple
T25322019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CTSS |
E634906
|
entity |
| Predicate | ranOnArchitecture |
P79620
|
FINISHED |
| Object | IBM 700/7000 series mainframes |
—
|
NE NERFINISHED |
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: IBM 700/7000 series mainframes | Statement: [CTSS, ranOnArchitecture, IBM 700/7000 series mainframes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ranOnArchitecture Context triple: [CTSS, ranOnArchitecture, IBM 700/7000 series mainframes]
-
A.
runsOnHardware
Indicates that a system, software, or process operates using or is executed on a specified hardware platform.
-
B.
ranOn
chosen
Indicates that an entity executed or operated on a particular platform, system, or environment.
-
C.
usesArchitecture
Indicates that one entity is built, implemented, or operates according to the architectural style, framework, or design specified by another entity.
-
D.
ranAs
Indicates that one entity previously operated or functioned in the role, capacity, or identity of another entity.
-
E.
hasArchitectureBy
Indicates that an entity’s architectural design was created or authored by a specified architect or architectural firm.
- F. None of above.
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_69e75a9847c08190bb02990d06d5ffb7 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f4969035ac8190a35a8f6c4e4685a7 |
completed | May 1, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69f45d06d0388190b36ecde92013624a |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 21, 2026, 1:28 p.m.