Triple
T1057026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levi-Civita connection |
E22817
|
entity |
| Predicate | yearIntroducedApprox |
P3297
|
FINISHED |
| Object | early 20th century |
—
|
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: early 20th century | Statement: [Levi-Civita connection, yearIntroducedApprox, early 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearIntroducedApprox Context triple: [Levi-Civita connection, yearIntroducedApprox, early 20th century]
-
A.
introducedInYear
chosen
Indicates the year in which something was first introduced, launched, or made available.
-
B.
incorporationYear
Indicates the calendar year in which an organization or entity was formally incorporated or legally established.
-
C.
wasFirstBuiltInYear
Indicates that the initial construction of an entity was completed in a specified year.
-
D.
destructionYear
Indicates the year in which an entity was destroyed or ceased to exist due to destructive events or actions.
-
E.
yearOfUse
Indicates the specific year during which something was in use or actively utilized.
- 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_69a493dada0481909c43649f9843ea91 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4ba6e35ac8190802341c31bda0e3b |
completed | March 1, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69a4b7340a048190807363f19d17a58f |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.