Triple
T13782013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | France 2 |
E331152
|
entity |
| Predicate | satelliteService |
P19767
|
FINISHED |
| Object | TNTSAT |
E337203
|
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: TNTSAT | Statement: [France 2, satelliteService, TNTSAT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TNTSAT Context triple: [France 2, satelliteService, TNTSAT]
-
A.
TNTSAT
chosen
TNTSAT is a French free-to-air satellite television platform that broadcasts the national digital terrestrial TV channels via satellite.
-
B.
DPLL(T)
DPLL(T) is a framework that extends the classic DPLL SAT-solving algorithm with theory solvers to efficiently decide satisfiability modulo background theories such as arithmetic, arrays, or bit-vectors.
-
C.
Boolector
Boolector is an efficient SMT solver specialized in bit-vectors, arrays, and uninterpreted functions, widely used in formal verification and model checking.
-
D.
CDCL SAT solver
A CDCL SAT solver is an advanced algorithm for solving Boolean satisfiability problems that extends the classic DPLL approach with conflict-driven clause learning and non-chronological backtracking to greatly improve efficiency on large, complex instances.
-
E.
SMTInterpol
SMTInterpol is an SMT solver focused on generating interpolants and solving satisfiability modulo theories problems, particularly over linear arithmetic and related theories.
- 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_69d81c58feb08190a77bca8bf7d6d20f |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0247ccc881908dad7b547221f15d |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b079013881908e9f5412e5dfb0b2 |
completed | May 3, 2026, 8:30 p.m. |
Created at: April 9, 2026, 10:11 p.m.