Triple
T37505069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curveball |
E932068
|
entity |
| Predicate | informationUsedIn |
P188170
|
FINISHED |
| Object | pre-war intelligence on Iraq |
—
|
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: pre-war intelligence on Iraq | Statement: [Curveball, informationUsedIn, pre-war intelligence on Iraq]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: informationUsedIn Context triple: [Curveball, informationUsedIn, pre-war intelligence on Iraq]
-
A.
usesInformationFor
Indicates that one entity applies or exploits information obtained from another entity for a particular purpose or activity.
-
B.
usedInforms
Indicates that one entity utilizes information from another entity to guide or shape its own actions, decisions, or outputs.
-
C.
usesInformationSources
Indicates that an entity relies on or consults specified information sources to perform actions, make decisions, or obtain knowledge.
-
D.
providesInformationIn
Indicates that one entity supplies or conveys information within or through another entity or context.
-
E.
usesDataIn
Indicates that one entity relies on, accesses, or incorporates data from another entity in performing its function or operation.
- F. None of above. chosen
Provenance (4 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_69fba5eec0448190a5e6f0c43fdcd0e3 |
completed | May 6, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69fba34edd548190bfa980e6e16e0a88 |
completed | May 6, 2026, 8:23 p.m. |
| PDg | Predicate description generation | batch_69fba5ee00fc81909be7b947a3f95034 |
completed | May 6, 2026, 8:34 p.m. |
Created at: May 3, 2026, 4:17 p.m.