Triple
T5360069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levi Eshkol |
E102996
|
entity |
| Predicate | managed |
P3234
|
FINISHED |
| Object | Mekorot |
E514538
|
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: Mekorot | Statement: [Levi Eshkol, managed, Mekorot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mekorot Context triple: [Levi Eshkol, managed, Mekorot]
-
A.
Mekorot
chosen
Mekorot is Israel’s national water company, responsible for developing and operating the country’s water infrastructure and supply systems.
-
B.
Valley of Sorek
The Valley of Sorek is a biblical valley in ancient Israel traditionally associated with the story of Samson and Delilah.
-
C.
Aviv Group
Aviv Group is an Israeli real estate development company known for undertaking major commercial and residential projects, including prominent skyscrapers.
-
D.
Telem (Israel)
Telem (Israel) was a short-lived centrist political party founded in the early 1980s by former Israeli Defense Minister Moshe Dayan.
-
E.
Gush Dan
Gush Dan is the densely populated metropolitan area centered around Tel Aviv on Israel’s Mediterranean coast, encompassing numerous surrounding cities and suburbs.
- 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_69bd43daa3e4819090b59d127db70e57 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd86330e4c8190b5452226886287b3 |
completed | March 20, 2026, 5:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf291c89c8819084b9305c3bddc3c0 |
completed | March 21, 2026, 11:26 p.m. |
Created at: March 20, 2026, 2:02 p.m.