Triple
T18275842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haim Arlosoroff |
E437730
|
entity |
| Predicate | trialRelatedTo |
P3137
|
FINISHED |
| Object | trial of Abba Ahimeir, Zvi Rosenblatt and Avraham Stavsky |
—
|
LITERAL 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: trial of Abba Ahimeir, Zvi Rosenblatt and Avraham Stavsky | Statement: [Haim Arlosoroff, trialRelatedTo, trial of Abba Ahimeir, Zvi Rosenblatt and Avraham Stavsky]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trialRelatedTo Context triple: [Haim Arlosoroff, trialRelatedTo, trial of Abba Ahimeir, Zvi Rosenblatt and Avraham Stavsky]
-
A.
relatedTrial
Indicates that one trial is associated with another trial, typically through relevance, similarity, or shared context within a broader study or legal/experimental framework.
-
B.
relatedStudy
Indicates that one study is connected or relevant to another study, typically through shared topics, methods, or findings.
-
C.
trialOccurredIn
Indicates that a particular trial took place within a specified location, venue, or jurisdiction.
-
D.
relatedTest
Indicates that there exists some form of connection or association between one test and another.
-
E.
relatedCase
chosen
Indicates that one legal case is connected or associated with another case, such as through shared facts, parties, issues, or procedural history.
- F. None of above.
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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50051bccc8190832eacdb6945d6b7 |
completed | April 19, 2026, 4:18 p.m. |
| PD | Predicate disambiguation | batch_69e44fd81c788190b08c6be3b07a08c5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:34 a.m.