Triple
T35207696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tekke Turkmens |
E1016583
|
entity |
| Predicate | opponentInBattleOfGeokTepe |
P182601
|
FINISHED |
| Object | Russian Empire |
—
|
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: Russian Empire | Statement: [Tekke Turkmens, opponentInBattleOfGeokTepe, Russian Empire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opponentInBattleOfGeokTepe Context triple: [Tekke Turkmens, opponentInBattleOfGeokTepe, Russian Empire]
-
A.
opponentInBattleOfRaphia
Indicates that two entities were opposing sides against each other in the historical Battle of Raphia.
-
B.
sideInBattleOfHunayn
Indicates that an entity participated as a side (party or faction) in the Battle of Hunayn.
-
C.
opponentStateAtBattleOfChangping
Indicates that the referenced entity was in an opposing position or role during the Battle of Changping.
-
D.
opponentAtBattleOfTheNile
Indicates that one entity was an opposing combatant of the other in the Battle of the Nile.
-
E.
opponentOfByzantines
Indicates a relationship where an entity is an adversary or enemy of the Byzantines in a conflict or rivalry.
- F. None of above. chosen
Provenance (4 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_69f76ddf549c8190869d0af076fd2c28 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7904a770481908ef3f788e51e8dba |
completed | May 3, 2026, 6:13 p.m. |
| PD | Predicate disambiguation | batch_69f78e2d71248190b850c2802ec170c0 |
completed | May 3, 2026, 6:04 p.m. |
| PDg | Predicate description generation | batch_69f78f629d508190b755848162c4e101 |
completed | May 3, 2026, 6:09 p.m. |
Created at: May 3, 2026, 4:02 p.m.