Triple
T26942064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thatta region |
E678546
|
entity |
| Predicate | wasImportantUnder |
P147736
|
FINISHED |
| Object | Samma dynasty |
—
|
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: Samma dynasty | Statement: [Thatta region, wasImportantUnder, Samma dynasty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasImportantUnder Context triple: [Thatta region, wasImportantUnder, Samma dynasty]
-
A.
lostImportanceUnder
Indicates that one entity’s importance or prominence decreased when another specified entity came into power, control, or influence.
-
B.
isImportantFor
Indicates that something holds significant value, relevance, or necessity in relation to something else.
-
C.
influentialUnder
Indicates that one entity is significantly shaped, guided, or affected by the influence or authority of another entity.
-
D.
wasProminent
Indicates that an entity held a position of significant importance, influence, or visibility within a particular context or period.
-
E.
gainedProminenceUnder
chosen
Indicates that an entity rose to greater importance, influence, or recognition during the leadership, authority, or period associated with another entity.
- 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_69eeeb4d69588190a7c912164a1c37b3 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f62081136c81909de8090b1d6c1ac5 |
completed | May 2, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:19 a.m.