Triple
T29961113
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The First Days of Spring |
E761042
|
entity |
| Predicate | followsNarrativeArc |
P86045
|
FINISHED |
| Object | breakup and recovery |
—
|
LITERAL 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: breakup and recovery | Statement: [The First Days of Spring, followsNarrativeArc, breakup and recovery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsNarrativeArc Context triple: [The First Days of Spring, followsNarrativeArc, breakup and recovery]
-
A.
followsStoryOf
Indicates that one narrative, account, or storyline continues from, is based on, or is derived from the events or structure of another.
-
B.
followsPlot
Indicates that one narrative element adheres to, continues, or is consistent with the storyline established by another.
-
C.
followsCharacterDevelopmentOf
Indicates that one entity’s narrative progression or growth is modeled on, parallels, or traces the character development arc of another entity.
-
D.
narrativeSequence
Indicates that one event or narrative element follows another in a temporal or logical storytelling order.
-
E.
isNarrativeDriven
chosen
Indicates that an entity’s primary structure or progression is guided by a storyline or plot rather than by mechanics, data, or other non-story elements.
- F. None of above.
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_69f22466327481908ba6db916837bece |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fcf825ca7081909d06b0df33eb33f9 |
completed | May 7, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fcf42160f0819096812a8bf590875e |
completed | May 7, 2026, 8:20 p.m. |
Created at: April 29, 2026, 6:29 p.m.