Triple
T3804468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Galmudug |
E91770
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object | Hobyo |
E395015
|
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: Hobyo | Statement: [Galmudug, hasPort, Hobyo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hobyo Context triple: [Galmudug, hasPort, Hobyo]
-
A.
Hobyo
chosen
Hobyo is a historic coastal town and port on the Indian Ocean in central Somalia, known for its strategic location and role in regional trade.
-
B.
Hobyot
Hobyot is a rare and severely endangered South Semitic language spoken by small communities in eastern Yemen and western Oman.
-
C.
Habikino
Habikino is a city in Osaka Prefecture, Japan, known for its historic kofun burial mounds and role within the Osaka metropolitan area.
-
D.
Ibura
Ibura is a populous residential neighborhood and district located in the southern zone of Recife, Brazil.
-
E.
Hob
Hob is a medieval English diminutive of the given name Robert, historically used as a familiar or nickname.
- 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_69aed96354f48190a768966d6bd19b04 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee7bc240881909e91b7b99403a13c |
completed | March 9, 2026, 3:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b51c70a98081908e86293f7e684649 |
completed | March 14, 2026, 8:29 a.m. |
Created at: March 9, 2026, 3:15 p.m.