Triple
T31323856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Otlukbeli |
E798826
|
entity |
| Predicate | hasPartOfDate |
P97750
|
FINISHED |
| Object | 1473 |
—
|
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: 1473 | Statement: [Battle of Otlukbeli, hasPartOfDate, 1473]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPartOfDate Context triple: [Battle of Otlukbeli, hasPartOfDate, 1473]
-
A.
hasDateWith
Indicates that one entity is scheduled to go on or is engaged in a romantic or social date with another entity.
-
B.
hasDateContext
Indicates that something is associated with, constrained by, or interpreted within a specific date or time-related context.
-
C.
isTemporalComponentOf
Indicates that one entity represents a temporal part, phase, or time-bounded segment within the overall duration or existence of another entity.
-
D.
hasVariableDate
Indicates that the associated date is not fixed but can change or vary depending on conditions or context.
-
E.
hasPartInYear
chosen
Indicates that something includes or contains a specific part, component, or segment that is associated with a particular year.
- 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_69f224e3238c8190b2291f50ea4962cd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fea2d0a4d08190aa06aeb902a02d5a |
completed | May 9, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fea24698348190b9b992a8e7cdbcd0 |
completed | May 9, 2026, 2:56 a.m. |
Created at: April 29, 2026, 9:15 p.m.