Triple
T3612632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marangu Route |
E76523
|
entity |
| Predicate | endpoint |
P32830
|
FINISHED |
| Object |
Kibo Hut
Kibo Hut is a high-altitude mountain refuge on Mount Kilimanjaro that serves as the main base camp for summit attempts via the Marangu Route.
|
E374030
|
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: Kibo Hut | Statement: [Marangu Route, endpoint, Kibo Hut]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kibo Hut Context triple: [Marangu Route, endpoint, Kibo Hut]
-
A.
Gonella Hut
Gonella Hut is a high-altitude mountain refuge on the Italian side of Mont Blanc, commonly used as a base for alpine ascents of the peak.
-
B.
Vallot Hut
Vallot Hut is a high-altitude emergency shelter on Mont Blanc used by climbers as a critical refuge during ascents via the Goûter Route.
-
C.
Moturau Hut
Moturau Hut is a backcountry accommodation hut located along New Zealand’s Kepler Track in Fiordland National Park, providing overnight shelter for trampers.
-
D.
Koya
Koya is a Dravidian language spoken primarily by the Koya tribal communities in parts of central and southern India.
-
E.
Nakasero Hill
Nakasero Hill is an upscale, central neighborhood in Kampala known for hosting government offices, embassies, luxury hotels, and commercial centers.
- 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: Kibo Hut Triple: [Marangu Route, endpoint, Kibo Hut]
Generated description
Kibo Hut is a high-altitude mountain refuge on Mount Kilimanjaro that serves as the main base camp for summit attempts via the Marangu Route.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kibo Hut Target entity description: Kibo Hut is a high-altitude mountain refuge on Mount Kilimanjaro that serves as the main base camp for summit attempts via the Marangu Route.
-
A.
Gonella Hut
Gonella Hut is a high-altitude mountain refuge on the Italian side of Mont Blanc, commonly used as a base for alpine ascents of the peak.
-
B.
Vallot Hut
Vallot Hut is a high-altitude emergency shelter on Mont Blanc used by climbers as a critical refuge during ascents via the Goûter Route.
-
C.
Moturau Hut
Moturau Hut is a backcountry accommodation hut located along New Zealand’s Kepler Track in Fiordland National Park, providing overnight shelter for trampers.
-
D.
Koya
Koya is a Dravidian language spoken primarily by the Koya tribal communities in parts of central and southern India.
-
E.
Nakasero Hill
Nakasero Hill is an upscale, central neighborhood in Kampala known for hosting government offices, embassies, luxury hotels, and commercial centers.
- 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_69ad85da0ba481908b3b48c69efe2b98 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc22e5b30819084184b730732c727 |
completed | March 8, 2026, 6:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b43316224081909372f1007becc663 |
completed | March 13, 2026, 3:53 p.m. |
| NEDg | Description generation | batch_69b4384ae2948190bb5b371ab35a9057 |
completed | March 13, 2026, 4:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b438db5e8c8190a6cfcbade88e7d46 |
completed | March 13, 2026, 4:18 p.m. |
Created at: March 8, 2026, 3:23 p.m.