Triple
T2629500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GNAT |
E59598
|
entity |
| Predicate | maintainedBy |
P86
|
FINISHED |
| Object | AdaCore |
E284613
|
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: AdaCore | Statement: [GNAT, maintainedBy, AdaCore]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AdaCore Context triple: [GNAT, maintainedBy, AdaCore]
-
A.
AdaCore
chosen
AdaCore is a software company specializing in high-integrity, safety- and security-critical development tools and compilers for the Ada programming language.
-
B.
gnat
GNAT is a free, open-source Ada compiler and toolchain that is part of the GNU Compiler Collection (GCC).
-
C.
Embarcadero
Embarcadero is a historic waterfront district in San Francisco known for its piers, ferry terminal, and scenic promenade along the bay.
-
D.
Embarcadero Technologies
Embarcadero Technologies is a software company best known for developing database tools and the Delphi rapid application development environment for Windows and cross-platform applications.
-
E.
GNATmake
GNATmake is the GNAT Ada compiler’s build tool that automatically manages multi-file project compilation and dependency tracking.
- 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_69ab4ac8596c8190b34997e73d9e991c |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd8c452508190b02e1630d725497a |
completed | March 7, 2026, 7:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afa04cf4e08190938687bfeb0ae353 |
completed | March 10, 2026, 4:38 a.m. |
Created at: March 6, 2026, 9:50 p.m.