Triple
T31993225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Persian army (Qajar) |
E816923
|
entity |
| Predicate | attemptedReformBy |
P48027
|
FINISHED |
| Object | Abbas Mirza |
—
|
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: Abbas Mirza | Statement: [Persian army (Qajar), attemptedReformBy, Abbas Mirza]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attemptedReformBy Context triple: [Persian army (Qajar), attemptedReformBy, Abbas Mirza]
-
A.
hasReformEffort
Indicates that an entity undertakes, is involved in, or is the subject of a deliberate effort to change, improve, or restructure a system, policy, or practice.
-
B.
canReform
Indicates that an entity has the ability or potential to change, improve, or be corrected from a previous state, behavior, or condition.
-
C.
subjectToReformBy
chosen
Indicates that an entity is undergoing or designated for changes, improvements, or restructuring carried out by another entity.
-
D.
advocatedReformOf
Indicates that one entity publicly supported or promoted changes to another entity, typically aiming to improve or modify its structure, policies, or practices.
-
E.
isPartOfReform
Indicates that an action, measure, or component belongs to, contributes to, or is included within a broader reform initiative or process.
- 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_69f6b49436b0819094e21603054d05d4 |
completed | May 3, 2026, 2:36 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:13 a.m.