Triple
T8248388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hydra |
E192900
|
entity |
| Predicate | supportsProtocol |
P203
|
FINISHED |
| Object | Subversion |
E184313
|
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: Subversion | Statement: [Hydra, supportsProtocol, Subversion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Subversion Context triple: [Hydra, supportsProtocol, Subversion]
-
A.
Subversion
chosen
Subversion is a centralized version control system used to manage and track changes to source code and other files in software development projects.
-
B.
SVN
SVN is the IATA airport code for Hunter Army Airfield, a U.S. military airfield located near Savannah, Georgia.
-
C.
SVN
SVN is the three-letter ISO 3166-1 alpha-3 country code assigned to Slovenia.
-
D.
Concurrent Versions System
Concurrent Versions System (CVS) is an early, widely used open-source version control system that manages changes to source code in collaborative software development.
-
E.
CollabNet
CollabNet is a software development and DevOps company best known for creating and stewarding the Subversion (SVN) version control system.
- 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_69ca82de7b8c81908d8106f8a53cff9b |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb78c6b3c48190a3ecebf449766124 |
completed | March 31, 2026, 7:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd3530ca148190a28761622d0cf663 |
completed | April 1, 2026, 3:09 p.m. |
Created at: March 30, 2026, 5:48 p.m.