Triple
T9264235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bridges |
E222655
|
entity |
| Predicate | usesTechnology |
P1485
|
FINISHED |
| Object | ODRADERIC (odradek scanner) |
E222658
|
NE 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: ODRADERIC (odradek scanner) | Statement: [Bridges, usesTechnology, ODRADERIC (odradek scanner)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ODRADERIC (odradek scanner) Context triple: [Bridges, usesTechnology, ODRADERIC (odradek scanner)]
-
A.
Odradek scanner
chosen
The Odradek scanner is a multifunctional, rotating sensor unit in Death Stranding that helps Sam Porter Bridges detect terrain, threats, and cargo-related information in the environment.
-
B.
OVDAS
OVDAS is a Chilean volcanic monitoring and surveillance agency responsible for observing and assessing volcanic activity across the country.
-
C.
Scanners
Scanners is a 1981 science fiction horror film directed by David Cronenberg, best known for its intense psychic warfare and iconic head-explosion scene.
-
D.
ODS
ODS is a major Czech centre-right political party known for its liberal-conservative ideology and significant role in the country’s post-communist politics.
-
E.
ODS
ODS is the United Nations’ online platform for publishing, accessing, and searching official UN documents in multiple languages.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca841f2e808190a64f4c31903a1332 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd0748a1f481909d9d876692cefccc |
completed | April 1, 2026, 11:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d09c0f0c6c81909f97ccc4c09e8072 |
completed | April 4, 2026, 5:05 a.m. |
Created at: March 30, 2026, 7:32 p.m.