Triple
T9918747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashaiman |
E185935
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Tema |
E182923
|
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 | Statement: [Ashaiman, adjacentTo, Tema]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tema Context triple: [Ashaiman, adjacentTo, Tema]
-
A.
Tema
chosen
Tema is a major port and industrial city on the Atlantic coast of Ghana, located east of the capital Accra.
-
B.
Tema
Tema is a biblical figure mentioned in the Old Testament, traditionally regarded as a descendant of Ishmael and associated with a region or tribe in northwestern Arabia.
-
C.
Tema
Tema is a city located within Egypt's Sohag Governorate, known as a regional center in Upper Egypt.
-
D.
Tema Mantse
Tema Mantse is the traditional Ga chief and custodian of customary authority for the coastal city of Tema in Ghana.
-
E.
Topic
Topic is a streaming service and digital media brand known for curated, often international and socially conscious films, series, and documentaries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca829b45f481909040f7b99a1976ed |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb5685a908190ab3e55b9bf9613f6 |
completed | April 2, 2026, 12:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d20dec42848190ab9f8663155df83f |
completed | April 5, 2026, 7:23 a.m. |
Created at: March 30, 2026, 8:42 p.m.