Triple
T7946586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jiangling |
E184512
|
entity |
| Predicate | typeOfGovernmentCenter |
P79968
|
FINISHED |
| Object | royal capital |
—
|
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: royal capital | Statement: [Jiangling, typeOfGovernmentCenter, royal capital]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfGovernmentCenter Context triple: [Jiangling, typeOfGovernmentCenter, royal capital]
-
A.
governmentalUnitType
Indicates the specific category or classification of a governmental unit (such as federal, state, municipal, or other administrative level) that an entity belongs to.
-
B.
governmentType
Indicates the form or system of governance under which an entity (such as a country or organization) is organized and ruled.
-
C.
governmentCenter
Indicates that a location serves as the primary administrative or political hub for a government or governing body.
-
D.
governmentTypeStrengthened
Indicates that the form or structure of a government has been reinforced, consolidated, or made more powerful or stable relative to its previous state.
-
E.
basedInGovernmentType
Indicates that an entity operates within or is associated with a government of a specified governmental system or type.
- 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_69ca8291c2008190b1b8832c87814bcf |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3b29a570819091a2ac185a8d57c4 |
completed | March 31, 2026, 3:10 a.m. |
| PD | Predicate disambiguation | batch_69cae93526d081909303265bf60419fd |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf788db1c8190839523e7777961d6 |
completed | March 30, 2026, 10:22 p.m. |
Created at: March 30, 2026, 5:09 p.m.