Triple
T9803777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archaeological Site of Cyrene |
E237903
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Shahhat |
E417705
|
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: Shahhat | Statement: [Archaeological Site of Cyrene, locatedIn, Shahhat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shahhat Context triple: [Archaeological Site of Cyrene, locatedIn, Shahhat]
-
A.
Shahhat
chosen
Shahhat is a town in northeastern Libya known for its proximity to the ancient Greek city of Cyrene and its location in the fertile Jabal al Akhdar region.
-
B.
Shamshabad
Shamshabad is a suburban area near Hyderabad in the Indian state of Telangana, known primarily for hosting the Rajiv Gandhi International Airport.
-
C.
Gulshanabad
Gulshanabad is the former historical name of the Indian city now known as Nashik in Maharashtra.
-
D.
Gulshanabad
Gulshanabad is a locality in the Medak region of Telangana, India, known primarily as the namesake of the Gulshanabad (Medak) administrative division.
-
E.
Sadulshahar
Sadulshahar is a town in the northern Indian state of Rajasthan, situated within the Ganganagar district near the border with Punjab.
- 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_69ca84dd4608819097ff4ed00feca280 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdab78832481909b184b21a8a46e50 |
completed | April 1, 2026, 11:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1c4538760819099ba1e392d31a135 |
completed | April 5, 2026, 2:09 a.m. |
Created at: March 30, 2026, 8:29 p.m.