Triple
T21274922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Jarash |
E524363
|
entity |
| Predicate | objectiveOfJordanianForces |
P129227
|
FINISHED |
| Object | expulsion of Palestinian guerrilla groups from Jordan |
—
|
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: expulsion of Palestinian guerrilla groups from Jordan | Statement: [Battle of Jarash, objectiveOfJordanianForces, expulsion of Palestinian guerrilla groups from Jordan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: objectiveOfJordanianForces Context triple: [Battle of Jarash, objectiveOfJordanianForces, expulsion of Palestinian guerrilla groups from Jordan]
-
A.
objectiveOfUSForces
Indicates that a specified goal, target, or mission serves as an objective assigned to or pursued by U.S. military forces.
-
B.
militaryObjectiveOfIsrael
Indicates that something is a target or goal designated as a military objective by Israel.
-
C.
militaryObjectiveOf
chosen
Indicates that something serves as a military target, goal, or purpose specifically associated with a given actor or force.
-
D.
objectiveOfIraq
Indicates that something is the goal, aim, or intended target associated with Iraq.
-
E.
unitJordan
Indicates that the subject is a Jordan block (or Jordan matrix) that has been normalized to have unit (typically 1) entries on its main diagonal.
- 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_69e0b516293c819089458ea2ec85f85e |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7365627a081908caea09097cca354 |
completed | April 21, 2026, 8:33 a.m. |
| PD | Predicate disambiguation | batch_69e5f6161dac8190b06009cd180e3ff7 |
completed | April 20, 2026, 9:47 a.m. |
Created at: April 16, 2026, 4:01 p.m.