Triple
T31993163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Lankaran |
E816921
|
entity |
| Predicate | countryAtTime (defender) |
P878
|
FINISHED |
| Object | Qajar Iran |
—
|
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: Qajar Iran | Statement: [Battle of Lankaran, countryAtTime (defender), Qajar Iran]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryAtTime (defender) Context triple: [Battle of Lankaran, countryAtTime (defender), Qajar Iran]
-
A.
countryOfDefender
Indicates the country to which the defending party or entity in a conflict, dispute, or legal case belongs.
-
B.
countryAtTheTime
chosen
Indicates that an entity is associated with a specific country as it existed at a particular point in time.
-
C.
historicallyDefendedBy
Indicates that an entity has, in the past, received protection or military defense from another entity.
-
D.
countryDuringBattle
Indicates that a specified country was involved in or existed as a relevant participant or context during a particular battle.
-
E.
countryGovernedDuringConflict
Indicates that a country was governed or administered by a particular authority or regime during a specified conflict or war.
- 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_69f348f8002081909a3588758ba94afb |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a001adc8c108190ab3a43f6415e2be3 |
completed | May 10, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_6a001a290330819097c2c3123f9014b4 |
completed | May 10, 2026, 5:39 a.m. |
Created at: May 1, 2026, 12:13 a.m.