Triple
T38331133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heartland Theory |
E1037824
|
entity |
| Predicate | laterElaborationYear |
P121968
|
FINISHED |
| Object | 1919 |
—
|
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: 1919 | Statement: [Heartland Theory, laterElaborationYear, 1919]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterElaborationYear Context triple: [Heartland Theory, laterElaborationYear, 1919]
-
A.
elaboratedInYear
chosen
Indicates that something was further developed, detailed, or expanded upon in a specific calendar year.
-
B.
yearOfRefinement
Indicates the specific year in which something was refined, improved, or updated from its previous form.
-
C.
laterPrefaceYear
Indicates that the preface associated with one entity was written or published in a later year than the preface associated with another entity.
-
D.
yearOfReference
Indicates the specific year to which a statement, measurement, or data point is intended to apply or be interpreted with reference.
-
E.
laterTypeStartYear
Indicates that the starting year of one type or classification occurs later in time than the starting year of another type or classification.
- 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_69f76e20d65c81909619ac0dd85c56f0 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a016cc5abcc8190b64094c777b40f6f |
completed | May 11, 2026, 5:44 a.m. |
| PD | Predicate disambiguation | batch_6a016b997ecc8190818207c57b9cbf17 |
completed | May 11, 2026, 5:39 a.m. |
Created at: May 3, 2026, 4:30 p.m.