Triple
T38292865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Safavid garrison of Isfahan |
E1022407
|
entity |
| Predicate | capitalDefenseForceOf |
P154840
|
FINISHED |
| Object | Isfahan |
—
|
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: Isfahan | Statement: [Safavid garrison of Isfahan, capitalDefenseForceOf, Isfahan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalDefenseForceOf Context triple: [Safavid garrison of Isfahan, capitalDefenseForceOf, Isfahan]
-
A.
defenseForces
Indicates a relationship where one entity serves as the military or protective force responsible for defending another entity.
-
B.
fortressDefended
Indicates that a fortress is actively protected against threats or attacks by some defending force.
-
C.
townDefendedBy
chosen
Indicates that a particular town is protected or guarded by a specified defending force or entity.
-
D.
hasApproximateDefendingForceSize
Indicates that an entity is associated with a defending force whose size is known only approximately rather than as an exact value.
-
E.
defensiveCapability
Indicates the ability or capacity of an entity to protect itself or others against threats, attacks, or harm.
- 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_69f76df190f081908d5aa02c8a9286d0 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fe6b7c785c8190aaab06019f571434 |
completed | May 8, 2026, 11:02 p.m. |
| PD | Predicate disambiguation | batch_69fe68edef20819081c77f9607b944dd |
completed | May 8, 2026, 10:51 p.m. |
Created at: May 3, 2026, 4:30 p.m.