Triple
T23413175
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Honolulu–Maui |
E560133
|
entity |
| Predicate | connectsCapitalWith |
P152160
|
FINISHED |
| Object | major neighbor island |
—
|
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: major neighbor island | Statement: [Honolulu–Maui, connectsCapitalWith, major neighbor island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsCapitalWith Context triple: [Honolulu–Maui, connectsCapitalWith, major neighbor island]
-
A.
connectsCapital
Indicates a relationship where one entity serves as the capital city that is officially linked to or associated with another entity, such as a country or region.
-
B.
hasCapitalConnected
Indicates that there is a direct connection or linkage between an entity and its capital city.
-
C.
connectsCapitalWithRegion
Indicates a relationship where a capital city is linked or associated with the larger region it belongs to.
-
D.
connectsCapitalToBorder
Indicates a relationship where a capital city is linked or directly connected to a border location or boundary.
-
E.
hasCapitalLink
Indicates a relationship in which one entity is connected to another by being its capital (typically the capital city of a region, state, or country).
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a5124a54819087a7ae2f8a5b3dc0 |
completed | April 29, 2026, 6:28 a.m. |
| PD | Predicate disambiguation | batch_69f061ed34288190a2e5e8cae03b0095 |
completed | April 28, 2026, 7:29 a.m. |
| PDg | Predicate description generation | batch_69f07cbbd7488190ab3c8ae7d0fb68bf |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 17, 2026, 5:39 p.m.