Triple
T999241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Italian invasion of France |
E21565
|
entity |
| Predicate | dateOfMilitaryAction |
P4661
|
FINISHED |
| Object | 1940-06-21 |
—
|
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: 1940-06-21 | Statement: [Italian invasion of France, dateOfMilitaryAction, 1940-06-21]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateOfMilitaryAction Context triple: [Italian invasion of France, dateOfMilitaryAction, 1940-06-21]
-
A.
invasionDate
chosen
Indicates the date on which an invasion event occurred or began.
-
B.
battleOccurredOn
Indicates that a specific battle took place at or on a particular location or date.
-
C.
hasMilitarySignificanceSince
Indicates that something has held military importance or strategic value starting from a specified point in time.
-
D.
yearOfBattle
Indicates the specific calendar year in which a particular battle took place.
-
E.
battleDateRelation
Indicates the temporal relationship specifying on which date a particular battle or combat event took place.
- 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_69a493c476b48190b41fc5e793171cc6 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4e3d8b081908e536928e7d6199d |
completed | March 1, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69a4b2b057c48190b9e42df9246b3757 |
completed | March 1, 2026, 9:42 p.m. |
Created at: March 1, 2026, 7:41 p.m.