Triple
T27178266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erin Lindsay |
E683112
|
entity |
| Predicate | worksInUnitType |
P28425
|
FINISHED |
| Object | specialized investigative unit |
—
|
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: specialized investigative unit | Statement: [Erin Lindsay, worksInUnitType, specialized investigative unit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksInUnitType Context triple: [Erin Lindsay, worksInUnitType, specialized investigative unit]
-
A.
worksInOrganizationType
Indicates that an entity is employed by or performs work within an organization of a specified type (e.g., company, nonprofit, government agency).
-
B.
worksWith
Indicates that two entities collaborate or perform tasks together in a shared work-related context.
-
C.
hasWorksIn
Indicates that one entity is employed by or performs their professional activities within the organization, location, or context represented by another entity.
-
D.
worksFor
Indicates that one entity is employed by or performs work on behalf of another entity, typically an organization or individual.
-
E.
associatedUnitType
chosen
Indicates that one entity is linked to or characterized by a particular type or category of unit.
- 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_69eefad086808190ab89816c0c300476 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f67c9fe7b48190b79b4041357edb49 |
completed | May 2, 2026, 10:37 p.m. |
| PD | Predicate disambiguation | batch_69f678cc272081909e5c70f1bc7407f0 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 27, 2026, 9:27 a.m.