Triple
T601323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tel Aviv |
E11499
|
entity |
| Predicate | mergedWith |
P77
|
FINISHED |
| Object | Jaffa |
E66822
|
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: Jaffa | Statement: [Tel Aviv, mergedWith, Jaffa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jaffa Context triple: [Tel Aviv, mergedWith, Jaffa]
-
A.
Jaffa
chosen
Jaffa is an ancient port city on the Mediterranean coast, now part of Tel Aviv-Yafo in Israel, known for its historic harbor, mixed Arab-Jewish population, and continuous habitation since antiquity.
-
B.
Ramla
Ramla is an Israeli city historically significant as a major religious and communal center for Karaite Jews.
-
C.
Ashdod
Ashdod is a major coastal city in southern Israel that serves as an important cultural and religious hub, including for the Karaite Jewish community.
-
D.
Bat Yam
Bat Yam is a coastal city in central Israel, located just south of Tel Aviv along the Mediterranean Sea.
-
E.
Tiberias
Tiberias is an ancient city in northern Israel on the western shore of the Sea of Galilee, historically significant as a major center of Jewish learning and pilgrimage.
- 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_69a4932779b881908688590d59c71900 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49d7a2180819086c7e9465a2d7432 |
completed | March 1, 2026, 8:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a566fce9808190931b7c88b5c5686f |
completed | March 2, 2026, 10:31 a.m. |
Created at: March 1, 2026, 7:35 p.m.