Triple
T12100827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koko |
E288184
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object |
Koko Port
Koko Port is a coastal seaport in Koko, Nigeria, serving as a regional hub for maritime trade and cargo handling.
|
E966336
|
NE FINISHED |
How this triple was built (4 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: Koko Port | Statement: [Koko, hasPort, Koko Port]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koko Port Context triple: [Koko, hasPort, Koko Port]
-
A.
Koko Marina
Koko Marina is a waterfront area in Hawaii Kai on the island of Oahu, known for its marina, residential neighborhoods, and recreational boating.
-
B.
Port of Banana
The Port of Banana is a small but strategically located seaport in the Democratic Republic of the Congo that serves as one of the country's key Atlantic Ocean access points.
-
C.
Naha Port
Naha Port is a major seaport in Naha, Okinawa, serving as a key hub for passenger ferries, cargo shipping, and cruise ships in Japan’s Ryukyu Islands.
-
D.
Kada Port
Kada Port is a coastal harbor in Wakayama, Japan, serving as the main departure point for ferries to the nearby Tomogashima Islands.
-
E.
Bata Port
Bata Port is a major seaport in Bata, Equatorial Guinea, serving as an important hub for the country’s maritime trade and transportation.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Koko Port Triple: [Koko, hasPort, Koko Port]
Generated description
Koko Port is a coastal seaport in Koko, Nigeria, serving as a regional hub for maritime trade and cargo handling.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Koko Port Target entity description: Koko Port is a coastal seaport in Koko, Nigeria, serving as a regional hub for maritime trade and cargo handling.
-
A.
Koko Marina
Koko Marina is a waterfront area in Hawaii Kai on the island of Oahu, known for its marina, residential neighborhoods, and recreational boating.
-
B.
Port of Banana
The Port of Banana is a small but strategically located seaport in the Democratic Republic of the Congo that serves as one of the country's key Atlantic Ocean access points.
-
C.
Naha Port
Naha Port is a major seaport in Naha, Okinawa, serving as a key hub for passenger ferries, cargo shipping, and cruise ships in Japan’s Ryukyu Islands.
-
D.
Kada Port
Kada Port is a coastal harbor in Wakayama, Japan, serving as the main departure point for ferries to the nearby Tomogashima Islands.
-
E.
Bata Port
Bata Port is a major seaport in Bata, Equatorial Guinea, serving as an important hub for the country’s maritime trade and transportation.
- F. None of above. chosen
Provenance (5 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_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9155576b48190849f0c3e079a935f |
completed | April 10, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f674eab481909859b5403741eddd |
completed | May 2, 2026, 1:04 p.m. |
| NEDg | Description generation | batch_69f6017f89d88190b766af7828794d87 |
completed | May 2, 2026, 1:51 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f60232d89881909f254da6deb7f321 |
completed | May 2, 2026, 1:54 p.m. |
Created at: April 8, 2026, 9:48 p.m.