Triple
T6073002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amboise |
E135329
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object | Baalbek |
E531936
|
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: Baalbek | Statement: [Amboise, twinTown, Baalbek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Baalbek Context triple: [Amboise, twinTown, Baalbek]
-
A.
Baalbek
chosen
Baalbek is an ancient city in Lebanon renowned for its monumental Roman temple complex and well-preserved archaeological ruins.
-
B.
Ṭarābulus
Ṭarābulus is the Arabic name for Tripoli, a major historic port city and the capital of Libya on the Mediterranean coast.
-
C.
Banias
Banias is a coastal city on the Mediterranean Sea in western Syria, known for its oil refinery and port facilities.
-
D.
Madaba
Madaba is a historic Jordanian city renowned for its Byzantine and Umayyad-era mosaics, especially the famous 6th-century mosaic map of the Holy Land.
-
E.
Byblos
Byblos is an ancient Phoenician port city in modern-day Lebanon, considered one of the oldest continuously inhabited cities in the world and a major center of early writing and trade.
- 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_69c00879e8048190b690717d19c5bc03 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05759d29481908912015e734ab943 |
completed | March 22, 2026, 8:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c11d3a37fc81909bbc1cdeec3205cf |
completed | March 23, 2026, 11 a.m. |
Created at: March 22, 2026, 4:11 p.m.