Triple
T37607933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghana Navy |
E935705
|
entity |
| Predicate | hasBase |
P2909
|
FINISHED |
| Object |
Tema Naval Base
Tema Naval Base is a key Ghanaian naval installation located in the port city of Tema, serving as a strategic hub for maritime security and naval operations in the Gulf of Guinea.
|
E2234175
|
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: Tema Naval Base | Statement: [Ghana Navy, hasBase, Tema Naval Base]
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: Tema Naval Base Triple: [Ghana Navy, hasBase, Tema Naval Base]
Generated description
Tema Naval Base is a key Ghanaian naval installation located in the port city of Tema, serving as a strategic hub for maritime security and naval operations in the Gulf of Guinea.
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_69f76ed0a85481909254a8a89090c826 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba9026df4819093c25a9373f32691 |
completed | May 6, 2026, 8:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40a80c24348190be3bebbd9685537a |
completed | June 28, 2026, 4:50 a.m. |
| NEDg | Description generation | batch_6a40a9100f208190a5c02a0b58bdcc64 |
completed | June 28, 2026, 4:54 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a40a99908548190acfc7149786dc43c |
completed | June 28, 2026, 4:56 a.m. |
Created at: May 3, 2026, 4:18 p.m.