Triple
T1576004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Raouché Rocks |
E33652
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Corniche Beirut |
E28919
|
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: Corniche Beirut | Statement: [Raouché Rocks, adjacentTo, Corniche Beirut]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Corniche Beirut Context triple: [Raouché Rocks, adjacentTo, Corniche Beirut]
-
A.
Corniche Beirut
chosen
Corniche Beirut is a popular seaside promenade in Beirut known for its Mediterranean views, palm-lined walkway, and vibrant social atmosphere.
-
B.
Ain Diab Corniche
Ain Diab Corniche is a popular oceanfront promenade and beach district in Casablanca known for its nightlife, restaurants, and seaside leisure activities.
-
C.
Corniche
Corniche is a prominent waterfront promenade in Doha, Qatar, known for its scenic views of the city skyline and Doha Bay.
-
D.
Corniche
Corniche is a famous waterfront promenade in Abu Dhabi known for its beaches, parks, and scenic views of the city’s skyline.
-
E.
Port of Beirut
The Port of Beirut is Lebanon’s principal maritime gateway and commercial hub on the Mediterranean Sea, historically central to the country’s trade and economy.
- 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_69a885f27a4c8190a4622252cdf54c00 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a908d2cffc819090f3d5cbebae3307 |
completed | March 5, 2026, 4:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad4696c34c8190826bc6ab4dad7c01 |
completed | March 8, 2026, 9:51 a.m. |
Created at: March 4, 2026, 7:27 p.m.