Triple
T15325438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King David Hotel bombing |
E366396
|
entity |
| Predicate | buildingWingTargeted |
P87277
|
FINISHED |
| Object | southern wing of the King David Hotel |
—
|
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: southern wing of the King David Hotel | Statement: [King David Hotel bombing, buildingWingTargeted, southern wing of the King David Hotel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buildingWingTargeted Context triple: [King David Hotel bombing, buildingWingTargeted, southern wing of the King David Hotel]
-
A.
targetedBuilding
chosen
Indicates that an entity intentionally directed an attack or operation toward a specific building.
-
B.
towerAttachment
Indicates that one entity is physically attached to or structurally connected with a tower.
-
C.
towerConstruction
Indicates the process or activity of building or erecting a tower structure.
-
D.
towerFunction
Indicates that one entity serves as a tower-like structure or performs the function of a tower in relation to another entity.
-
E.
wingOf
Indicates that something is a wing that forms a physical or functional part of another entity.
- 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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dfd8f048190831b463a2728eafe |
completed | April 16, 2026, 1:40 a.m. |
| PD | Predicate disambiguation | batch_69deca9659f48190b8661df223ce5078 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:16 a.m.