Triple
T26050349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Erzurum (1877–1878) |
E647953
|
entity |
| Predicate | placeOfSiege |
P92602
|
FINISHED |
| Object | Erzurum fortress |
—
|
NE NERFINISHED |
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: Erzurum fortress | Statement: [Battle of Erzurum (1877–1878), placeOfSiege, Erzurum fortress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: placeOfSiege Context triple: [Battle of Erzurum (1877–1878), placeOfSiege, Erzurum fortress]
-
A.
siegeOccurredIn
chosen
Indicates that a siege took place within or at the location specified by the related entity.
-
B.
siegeRelated
Indicates a relationship in which one entity is involved with, associated with, or relevant to a siege or siege-related activities.
-
C.
typeOfSiege
Indicates the specific kind or category of siege involved in a conflict or military operation.
-
D.
isSiegeOf
Indicates a relationship where one event or action constitutes the military siege of a particular place, target, or entity.
-
E.
resultOfSiege
Indicates that one entity is the outcome or consequence produced by a siege conducted against 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_69e77e8d419481908004e6318d28aaab |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f676c440708190a4b9974e95d2291a |
completed | May 2, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f675fd59608190b246383435e68fce |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 22, 2026, 9:10 a.m.