Triple
T4101338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jebel Nafusa |
E87946
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object |
Yafran
Yafran is a town in western Libya situated in the Nafusa Mountains, known for its Berber heritage and strategic highland location.
|
E414090
|
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: Yafran | Statement: [Jebel Nafusa, nearbyCity, Yafran]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yafran Context triple: [Jebel Nafusa, nearbyCity, Yafran]
-
A.
Azania
Azania is a name used by some African liberation movements and activists to refer to a decolonized, non-apartheid South Africa.
-
B.
Martos
Martos is a historic town in southern Spain’s Andalusia region, known for its olive oil production and hilltop setting dominated by a medieval castle.
-
C.
Shuafat
Shuafat is a Palestinian neighborhood and refugee camp in East Jerusalem known for its dense population, complex political status, and challenging living conditions.
-
D.
Andal
Andal is a revered female Tamil Vaishnavite saint and poet, celebrated for her devotional hymns to Vishnu and her central place in the Sri Vaishnavism tradition.
-
E.
Aqrabi
Aqrabi was a small sultanate and tribal territory in what is now southern Yemen, historically incorporated into the British-backed Federation of South Arabia.
- 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: Yafran Triple: [Jebel Nafusa, nearbyCity, Yafran]
Generated description
Yafran is a town in western Libya situated in the Nafusa Mountains, known for its Berber heritage and strategic highland location.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Yafran Target entity description: Yafran is a town in western Libya situated in the Nafusa Mountains, known for its Berber heritage and strategic highland location.
-
A.
Azania
Azania is a name used by some African liberation movements and activists to refer to a decolonized, non-apartheid South Africa.
-
B.
Martos
Martos is a historic town in southern Spain’s Andalusia region, known for its olive oil production and hilltop setting dominated by a medieval castle.
-
C.
Shuafat
Shuafat is a Palestinian neighborhood and refugee camp in East Jerusalem known for its dense population, complex political status, and challenging living conditions.
-
D.
Andal
Andal is a revered female Tamil Vaishnavite saint and poet, celebrated for her devotional hymns to Vishnu and her central place in the Sri Vaishnavism tradition.
-
E.
Aqrabi
Aqrabi was a small sultanate and tribal territory in what is now southern Yemen, historically incorporated into the British-backed Federation of South Arabia.
- 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_69aed94564cc8190a9c1457daedb6e7f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0ed168819093c83ba079d6725c |
completed | March 9, 2026, 5:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b56b7833b081909bf5a87ee709b49f |
completed | March 14, 2026, 2:06 p.m. |
| NEDg | Description generation | batch_69b56f33f7688190a017e4486a3ba542 |
completed | March 14, 2026, 2:22 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b56fafb8208190997b6d91c4a1774d |
completed | March 14, 2026, 2:24 p.m. |
Created at: March 9, 2026, 3:40 p.m.