Triple
T22397102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Allegiant |
E553663
|
entity |
| Predicate | follows |
P134
|
FINISHED |
| Object | Insurgent |
—
|
NE NERFINISHED |
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: Insurgent | Statement: [Allegiant, follows, Insurgent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Insurgent Context triple: [Allegiant, follows, Insurgent]
-
A.
Insurgent
chosen
"Insurgent" is a 2015 science-fiction action film based on Veronica Roth's novel, serving as the second installment in the Divergent series.
-
B.
Allegiant
Allegiant is a 2016 science-fiction action film in the Divergent series, based on Veronica Roth’s novel, that continues the story of a dystopian, faction-based future society.
-
C.
Divergent
Divergent is a 2014 dystopian science-fiction film, based on Veronica Roth’s novel, set in a faction-divided future society and starring Shailene Woodley alongside Kate Winslet.
-
D.
Dauntless
Dauntless is one of the five factions in the Divergent series, known for valuing bravery, fearlessness, and combat prowess.
-
E.
Dauntless
Dauntless is the nickname of the Douglas SBD Dauntless, a World War II U.S. Navy dive bomber famed for its decisive role in battles such as Midway.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1585f67108190b8d3f23eaa0ed120 |
completed | April 29, 2026, 1:01 a.m. |
Created at: April 16, 2026, 8:45 p.m.