Triple
T9525938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torpex |
E229759
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | TNT |
E806161
|
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: TNT | Statement: [Torpex, contains, TNT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TNT Context triple: [Torpex, contains, TNT]
-
A.
TNT
TNT is an American cable television network known for airing sports, movies, and original drama programming.
-
B.
TNT
TNT is France's digital terrestrial television platform that broadcasts multiple free-to-air channels nationwide.
-
C.
TNT
chosen
TNT (trinitrotoluene) is a widely used high explosive known for its stability, ease of handling, and role as a standard measure of explosive power.
-
D.
Tank
Tank is a London-based art and fashion magazine known for its independent, avant-garde editorial approach and collaborations with experimental cultural projects.
-
E.
Tank
Tank is a German aeronautical engineer best known for designing the Focke-Wulf Fw 190 fighter aircraft used by the Luftwaffe during World War II.
- 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_69ca847870a881909d8d751a7d29da39 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd989b529c81909ee18dd3d468c816 |
completed | April 1, 2026, 10:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1527253588190ac365203ef382a2d |
completed | April 4, 2026, 6:03 p.m. |
Created at: March 30, 2026, 7:59 p.m.