Triple
T35990990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baghdad–Kirkuk highway |
E1040843
|
entity |
| Predicate | hasMajorCityConnected |
P65699
|
FINISHED |
| Object | Kirkuk |
E236794
|
NE 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: Kirkuk | Statement: [Baghdad–Kirkuk highway, hasMajorCityConnected, Kirkuk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMajorCityConnected Context triple: [Baghdad–Kirkuk highway, hasMajorCityConnected, Kirkuk]
-
A.
hasMajorCityOnRoute
chosen
Indicates that a major city lies along, or is directly served by, a specified route or path between locations.
-
B.
hasCapitalConnected
Indicates that there is a direct connection or linkage between an entity and its capital city.
-
C.
hasMajorCity
Indicates that a location possesses at least one city of significant size, importance, or influence within its region or country.
-
D.
hasMajorCityOfUse
Indicates that a particular city is the primary or most significant location where something (e.g., a product, language, service) is predominantly used or applied.
-
E.
hasMajorCityHub
Indicates that an entity contains or is associated with a primary, high-importance city that functions as a central hub for activity, services, or connectivity.
- F. None of above.
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_69f76e29084c819083987b828d414de7 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a031045669c8190944781a48d09b5b6 |
completed | May 12, 2026, 11:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3dfabb151c8190b0ea58ab502bb5ab |
completed | June 26, 2026, 4:06 a.m. |
| PD | Predicate disambiguation | batch_6a030fa775848190839b388f950d0364 |
completed | May 12, 2026, 11:31 a.m. |
Created at: May 3, 2026, 4:07 p.m.