Triple
T11781286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orangi Town |
E280151
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Manghopir |
E276941
|
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: Manghopir | Statement: [Orangi Town, locatedNear, Manghopir]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Manghopir Context triple: [Orangi Town, locatedNear, Manghopir]
-
A.
Manghopir
chosen
Manghopir is a historic neighborhood in Karachi, Pakistan, known for its Sufi shrine of Pir Mangho and natural hot and cold springs.
-
B.
Sekadau
Sekadau is a town and regency capital in the Indonesian province of West Kalimantan on the island of Borneo.
-
C.
Habis
Habis is an Arabic masculine given name commonly used in Jordan and other parts of the Arab world.
-
D.
Bamanankan
Bamanankan is a Mande language widely spoken in Mali and neighboring West African countries, particularly by the Bambara people.
-
E.
Sepetiba
Sepetiba is a coastal neighborhood in Rio de Janeiro known for its bay, fishing activities, and industrial port area.
- 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_69d6ab01d2688190ad8ed6bda487eaa5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a58413048190b9e3b9d2f5383ec3 |
completed | April 10, 2026, 7:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f090c828f0819097662c048542b5da |
completed | April 28, 2026, 10:49 a.m. |
Created at: April 8, 2026, 9:42 p.m.