Triple
T13682895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jump Week |
E328044
|
entity |
| Predicate | follows |
P134
|
FINISHED |
| Object | Tower Week |
E1054861
|
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: Tower Week | Statement: [Jump Week, follows, Tower Week]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tower Week Context triple: [Jump Week, follows, Tower Week]
-
A.
Tower Week
chosen
Tower Week is the intermediate training phase at the U.S. Army Airborne School where students practice parachute techniques from training towers to prepare for actual jump operations.
-
B.
Bright Week
Bright Week is the joyful week-long celebration in Eastern Christianity that immediately follows Easter, marked by festive liturgies and the continued proclamation of Christ’s resurrection.
-
C.
Magic Weekend
Magic Weekend is an annual rugby league event in which an entire round of Super League fixtures is played over one weekend at a single stadium.
-
D.
Toonami
Toonami is an action-oriented programming block known for airing anime and animated series, originally broadcast on Cartoon Network.
-
E.
Paris Games Week
Paris Games Week is a major annual video game trade fair in Paris that showcases upcoming games, hardware, and industry innovations to the public and professionals.
- 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_69d8076f1fa8819094664a59b55010df |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc66e75188190a9e82fdc5eb26513 |
completed | April 12, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f79d4a4a50819098bd4348eba19ee7 |
completed | May 3, 2026, 7:08 p.m. |
Created at: April 9, 2026, 9:53 p.m.