Triple
T58652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1st Marine Division (United States) |
E1161
|
entity |
| Predicate | formedIn |
P1515
|
FINISHED |
| Object | 1941 |
—
|
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: 1941 | Statement: [1st Marine Division (United States), formedIn, 1941]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formedIn Context triple: [1st Marine Division (United States), formedIn, 1941]
-
A.
formedBy
Indicates that something comes into existence or is created as a result of a specific agent, process, or combination of components.
-
B.
formed
Indicates that one entity came into existence, shape, or organization as a result of the actions or processes involving another entity.
-
C.
formedInYear
chosen
Indicates the year in which an entity was originally established, created, or came into existence.
-
D.
formedByUnionOf
Indicates that something is created or defined as the union or combination of multiple other things.
-
E.
formOfRecognition
Indicates a relationship where one entity serves as an official acknowledgment, honor, or validation granted to another entity.
- 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_69a248adc5b48190aa8db9fb092fb28a |
completed | Feb. 28, 2026, 1:45 a.m. |
| NER | Named-entity recognition | batch_69a24c9057348190aa6692eeeae19569 |
completed | Feb. 28, 2026, 2:01 a.m. |
| PD | Predicate disambiguation | batch_69a24ac7547c81909bb68f327cdb9158 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:50 a.m.