Triple
T30943598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Cities of America |
E788325
|
entity |
| Predicate | hasStateOf |
P197262
|
FINISHED |
| Object | fragmented nation |
—
|
LITERAL FINISHED |
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: fragmented nation | Statement: [United Cities of America, hasStateOf, fragmented nation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStateOf Context triple: [United Cities of America, hasStateOf, fragmented nation]
-
A.
hasStateSystem
Indicates that an entity possesses, follows, or is governed by a particular system of state organization, rules, or governance.
-
B.
hadStateFrom
Indicates that an entity possessed or was in a particular state starting from a specified point in time.
-
C.
hasSubjectState
Indicates that an entity (typically an event, statement, or situation) is associated with a particular state or condition of its subject.
-
D.
hasWorldState
Indicates that an entity is associated with, or exists within, a particular overall configuration or condition of the world at a given time.
-
E.
hasMemberState
Indicates that an entity includes or comprises another entity as one of its constituent member states within a larger organizational or political structure.
- 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_69f224c180f88190ad177372ee02b7e2 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe831c97c88190b27ecf100e25c2a0 |
completed | May 9, 2026, 12:43 a.m. |
| PD | Predicate disambiguation | batch_69fe7f1b92648190b14e56bcaee5d0ca |
completed | May 9, 2026, 12:26 a.m. |
| PDg | Predicate description generation | batch_69fe831ba4708190a5564afd7d5a4319 |
completed | May 9, 2026, 12:43 a.m. |
Created at: April 29, 2026, 8:53 p.m.