Triple
T4884437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lebanon–Israel border |
E109405
|
entity |
| Predicate | passesNear |
P416
|
FINISHED |
| Object |
Metula
Metula is a northern Israeli town known for being the country’s northernmost settlement and a key agricultural and tourism center in the Upper Galilee.
|
E477625
|
NE FINISHED |
How this triple was built (4 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: Metula | Statement: [Lebanon–Israel border, passesNear, Metula]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Metula Context triple: [Lebanon–Israel border, passesNear, Metula]
-
A.
Sivan
Sivan is the third month of the Hebrew calendar, traditionally associated with the festival of Shavuot and the giving of the Torah.
-
B.
Adar
Adar is the twelfth month of the Hebrew calendar, traditionally associated with the festival of Purim and themes of joy and celebration.
-
C.
Shevat
Shevat is the eleventh month of the Hebrew calendar, typically falling in January–February in the Gregorian calendar.
-
D.
Nisan
Nisan is the first month of the Hebrew religious year, traditionally associated with spring and the festival of Passover.
-
E.
Iyar
Iyar is the second month of the Hebrew calendar’s religious year, falling in spring and associated with events such as Israel’s Independence Day and Lag BaOmer.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Metula Triple: [Lebanon–Israel border, passesNear, Metula]
Generated description
Metula is a northern Israeli town known for being the country’s northernmost settlement and a key agricultural and tourism center in the Upper Galilee.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Metula Target entity description: Metula is a northern Israeli town known for being the country’s northernmost settlement and a key agricultural and tourism center in the Upper Galilee.
-
A.
Sivan
Sivan is the third month of the Hebrew calendar, traditionally associated with the festival of Shavuot and the giving of the Torah.
-
B.
Adar
Adar is the twelfth month of the Hebrew calendar, traditionally associated with the festival of Purim and themes of joy and celebration.
-
C.
Shevat
Shevat is the eleventh month of the Hebrew calendar, typically falling in January–February in the Gregorian calendar.
-
D.
Nisan
Nisan is the first month of the Hebrew religious year, traditionally associated with spring and the festival of Passover.
-
E.
Iyar
Iyar is the second month of the Hebrew calendar’s religious year, falling in spring and associated with events such as Israel’s Independence Day and Lag BaOmer.
- F. None of above. chosen
Provenance (5 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_69bd440f71348190b99938e59fb7f9a1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6de253ac8190b1112da6953fa4f2 |
completed | March 20, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be680bf12c8190a5da2c7f0088cec2 |
completed | March 21, 2026, 9:42 a.m. |
| NEDg | Description generation | batch_69be6c25d3448190b2589959a2f221c8 |
completed | March 21, 2026, 10 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be6cf6662c8190bc1b94766c5da1e9 |
completed | March 21, 2026, 10:03 a.m. |
Created at: March 20, 2026, 1:27 p.m.