Triple
T11446317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ricki Tarr |
E271274
|
entity |
| Predicate | helpsUncover |
P87311
|
FINISHED |
| Object | high-level Soviet mole in British intelligence |
—
|
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: high-level Soviet mole in British intelligence | Statement: [Ricki Tarr, helpsUncover, high-level Soviet mole in British intelligence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: helpsUncover Context triple: [Ricki Tarr, helpsUncover, high-level Soviet mole in British intelligence]
-
A.
helpedDiscover
chosen
Indicates that one entity assisted another entity in the process of discovering or uncovering something.
-
B.
helpsInvestigate
Indicates that one entity assists another entity in carrying out an investigation or inquiry.
-
C.
covered
Indicates that one entity lies over or on top of another entity so as to conceal, protect, or obscure it.
-
D.
decipheredWithHelpOf
Indicates that something was successfully deciphered or interpreted through assistance provided by another entity or resource.
-
E.
helpsIdentify
Indicates a relationship where one entity serves to distinguish, recognize, or determine the identity or characteristics 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_69d6aadff8888190a13f253f0d460874 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d81c6d4890819082fb4a670feb2629 |
completed | April 9, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69d7e7162b288190a0bfb89f7eb747c7 |
completed | April 9, 2026, 5:51 p.m. |
Created at: April 8, 2026, 9:35 p.m.