Triple
T25967991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | جيبوتي |
E645726
|
entity |
| Predicate | أهم_الموانئ |
P58536
|
FINISHED |
| Object | ميناء جيبوتي |
—
|
NE NERFINISHED |
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: ميناء جيبوتي | Statement: [جيبوتي, أهم_الموانئ, ميناء جيبوتي]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: أهم_الموانئ Context triple: [جيبوتي, أهم_الموانئ, ميناء جيبوتي]
-
A.
isMainHarbourOf
chosen
Indicates that a harbour serves as the primary or principal port facility for a specified location or region.
-
B.
isAmongLargestPortsIn
Indicates that a port ranks among the largest ports within a specified geographic or administrative area.
-
C.
isBusiestSeaportIn
Indicates that a seaport handles the highest volume of traffic or activity compared to all other seaports within a specified region or area.
-
D.
harbours
Indicates that one entity provides shelter, refuge, or concealment for another, often by keeping it safe or hidden.
-
E.
isLargestSeaportOn
Indicates that a seaport is the largest seaport located on a specified geographic feature, such as a coast, island, or body of water.
- 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_69e77e8768648190b27bb578f14bcb88 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f604cc423081908edb1fcf694f06fc |
completed | May 2, 2026, 2:06 p.m. |
| PD | Predicate disambiguation | batch_69f4a10480748190a2e67bd399fc435d |
completed | May 1, 2026, 12:48 p.m. |
Created at: April 22, 2026, 8:50 a.m.