Triple
T1011635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leningrad, Russian SFSR, Soviet Union |
E21835
|
entity |
| Predicate | approximateSiegeDurationDays |
P11968
|
FINISHED |
| Object | 872 |
—
|
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: 872 | Statement: [Leningrad, Russian SFSR, Soviet Union, approximateSiegeDurationDays, 872]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateSiegeDurationDays Context triple: [Leningrad, Russian SFSR, Soviet Union, approximateSiegeDurationDays, 872]
-
A.
battleDuration
chosen
Indicates the length of time for which a particular battle or combat event lasts.
-
B.
isSiegeOf
Indicates a relationship where one event or action constitutes the military siege of a particular place, target, or entity.
-
C.
numberOfDaysOfWar
Indicates the total count of days during which a state of war or active armed conflict persists.
-
D.
durationUntil
Indicates the length of time remaining from a given starting point until a specified future event or state occurs.
-
E.
typicalDurationDays
Indicates the usual or expected number of days that an associated event, process, or state typically lasts.
- 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_69a493c68e24819080ed0ee8bcfd5ce0 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7be907c8190b5c6ea89257755a7 |
completed | March 1, 2026, 10:03 p.m. |
| PD | Predicate disambiguation | batch_69a4b72207c08190a3dbb2aa7acbbc71 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.