Triple
T1548636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rafi |
E33035
|
entity |
| Predicate | splitFrom |
P909
|
FINISHED |
| Object | Mapai |
E30738
|
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: Mapai | Statement: [Rafi, splitFrom, Mapai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mapai Context triple: [Rafi, splitFrom, Mapai]
-
A.
Mapai
chosen
Mapai was a dominant left-wing labor Zionist political party in pre-state and early Israel that played a central role in founding and governing the country.
-
B.
Mapam
Mapam was a left-wing socialist Zionist political party in Israel that played a significant role in the early decades of the state, particularly within the kibbutz movement and peace-oriented politics.
-
C.
Mapah
Mapah is Rabbi Moses Isserles’s glosses on the Shulchan Aruch, integrating Ashkenazi customs and rulings into that foundational Jewish legal code.
-
D.
MAP
MAP was the abbreviated name used for the United Kingdom’s Ministry of Aircraft Production, the World War II government department responsible for overseeing and increasing aircraft manufacturing.
-
E.
#MAPA
#MAPA is a hashtag used within the Fridays for Future movement to highlight and organize climate activism by communities in the Most Affected People and Areas.
- 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_69a885ee6db8819099502bc5ce8af881 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90856642c81909d88a679eb265b10 |
completed | March 5, 2026, 4:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad30a29ae88190ab1b2ca97b8ed09c |
completed | March 8, 2026, 8:17 a.m. |
Created at: March 4, 2026, 7:26 p.m.