Triple
T4013964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Province, Sri Lanka |
E90710
|
entity |
| Predicate | significantCity |
P12871
|
FINISHED |
| Object | Mannar |
E386427
|
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: Mannar | Statement: [Northern Province, Sri Lanka, significantCity, Mannar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mannar Context triple: [Northern Province, Sri Lanka, significantCity, Mannar]
-
A.
Mannar region
chosen
The Mannar region is a coastal area in northwestern Sri Lanka known for its shallow lagoons, rich marine biodiversity, and historical role as a trading hub.
-
B.
Mapun
Mapun is an Austronesian language spoken primarily by the Mapun people of the southern Philippines, particularly on Mapun (Cagayan de Sulu) Island in the Sulu Sea.
-
C.
Maa
Maa is a Nilotic language spoken primarily by the Maasai people of Kenya and Tanzania.
-
D.
Ballimaran
Ballimaran is a historic, densely packed lane in Old Delhi known for its traditional shops, old havelis, and association with the poet Mirza Ghalib.
-
E.
Eivissa
Eivissa is the Catalan name for Ibiza, a popular Mediterranean island in Spain’s Balearic archipelago known for its beaches and nightlife.
- 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_69aed95e44088190aff7d90a151b1b20 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefa8ad6348190b71feaf8c18c90c2 |
completed | March 9, 2026, 4:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b54c73e6048190a59a8d8bc12c907d |
completed | March 14, 2026, 11:54 a.m. |
Created at: March 9, 2026, 3:35 p.m.