Triple
T37505081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curveball |
E932068
|
entity |
| Predicate | allegedWorkplace |
P146199
|
FINISHED |
| Object | Iraqi mobile biological weapons facilities |
—
|
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: Iraqi mobile biological weapons facilities | Statement: [Curveball, allegedWorkplace, Iraqi mobile biological weapons facilities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allegedWorkplace Context triple: [Curveball, allegedWorkplace, Iraqi mobile biological weapons facilities]
-
A.
locationOfWork
Indicates the place or site where an entity performs its work or carries out its professional activities.
-
B.
placeInWork
Indicates that one entity is located or occurs within the spatial or structural context of another entity in a work.
-
C.
associatedWithWorkplace
chosen
Indicates a relationship where an entity has a connection or affiliation with a particular workplace or place of employment.
-
D.
ownsWork
Indicates that one entity has legal ownership or proprietary rights over a particular work or creation.
-
E.
workplaceAtTimeOfAttack
Indicates that the specified location was the person’s workplace at the time the attack occurred.
- 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_69f76ec5268481909ea01c73aeeefd42 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fce28d6c3081908bf76f5db63ecf68 |
completed | May 7, 2026, 7:05 p.m. |
| PD | Predicate disambiguation | batch_69fce12d2f08819082134b5eb3db6a24 |
completed | May 7, 2026, 6:59 p.m. |
Created at: May 3, 2026, 4:17 p.m.