Triple
T31644314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Merv oasis |
E807540
|
entity |
| Predicate | supportedCityType |
P57766
|
FINISHED |
| Object | fortified city |
—
|
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: fortified city | Statement: [Merv oasis, supportedCityType, fortified city]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedCityType Context triple: [Merv oasis, supportedCityType, fortified city]
-
A.
supportsCity
Indicates that one entity provides assistance, resources, or backing to a city, helping it function, develop, or achieve its goals.
-
B.
supportsCityCluster
Indicates that one entity provides the necessary resources, infrastructure, or services for a specific city cluster to function or develop.
-
C.
cityServedType
chosen
Indicates the type or category of city that is served by a given entity (such as a facility, service, or infrastructure).
-
D.
hostCitiesInclude
Indicates that a particular set, event, or organization has among its host locations the specified city or cities.
-
E.
connectsTypeOfCity
Indicates a relationship where one entity is linked to another as a specific type or category of city.
- 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_69f348d9ce58819093ea2da83cbeeec1 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e7aa0c8190bdc9ee4d54fc821b |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 30, 2026, 10:50 p.m.