Triple
T3077407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Homeland Security Investigations |
E64169
|
entity |
| Predicate | hasOperationalComponent |
P45730
|
FINISHED |
| Object | HSI field offices |
—
|
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: HSI field offices | Statement: [Homeland Security Investigations, hasOperationalComponent, HSI field offices]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOperationalComponent Context triple: [Homeland Security Investigations, hasOperationalComponent, HSI field offices]
-
A.
hasOperatingMIC
Indicates that an entity operates or manages a specific MIC (Market Identifier Code) in a financial or trading context.
-
B.
fullyOperationalBy
Indicates that an entity is expected or required to be completely functional and ready for use no later than a specified time or event.
-
C.
hasWorkingMode
Indicates that an entity operates under or supports a particular mode or configuration of functioning.
-
D.
hasGlobalOperationsIn
Indicates that an entity conducts business or operational activities across multiple countries within the specified region or location.
-
E.
hasServerComponent
Indicates that an entity includes, depends on, or is associated with a particular server-side component.
- 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_69ad857a8aec8190bfdfd9c14554ac5a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada1a6f6148190ae5cd6e45eda9006 |
completed | March 8, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69ad9debb6308190be28378ae1fc98af |
completed | March 8, 2026, 4:03 p.m. |
| PDg | Predicate description generation | batch_69ada0f6fef48190b13898be383a246b |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 8, 2026, 3:02 p.m.