Triple
T4815781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khertvisi Fortress |
E107583
|
entity |
| Predicate | battledBy |
P18835
|
FINISHED |
| Object | Mongol forces |
—
|
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: Mongol forces | Statement: [Khertvisi Fortress, battledBy, Mongol forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: battledBy Context triple: [Khertvisi Fortress, battledBy, Mongol forces]
-
A.
battledIn
Indicates that two or more entities engaged in a battle or conflict that took place at a specific location or during a particular event.
-
B.
battleOpponent
chosen
Indicates that two entities are engaged in or designated as opponents in a battle or combat scenario.
-
C.
battleAlsoKnownAs
Indicates that a particular battle is known by an alternative name or names.
-
D.
associatedWithBattle
Indicates a relationship where an entity is connected or linked to a specific battle, such as by participation, relevance, or involvement.
-
E.
defeatedBy
Indicates that one entity has been beaten, overcome, or conquered by another in a contest, conflict, or competition.
- 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_69bd43f9efa081908314cb3e94fa1695 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ddd17d881909f7731ff2b460e83 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c1dfa3481909d240d50ed0ee38c |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:23 p.m.