Triple
T9397176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Lighthouse |
E226171
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | RT Features |
E268527
|
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: RT Features | Statement: [The Lighthouse, productionCompany, RT Features]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RT Features Context triple: [The Lighthouse, productionCompany, RT Features]
-
A.
RT Features
chosen
RT Features is a Brazilian film production company known for backing acclaimed independent and auteur-driven films, including collaborations with prominent international directors.
-
B.
RT
RT is the commonly used abbreviation for Rotten Tomatoes, a popular website that aggregates film and television reviews and ratings.
-
C.
RT
RT is a Russian state-funded international television network and online media outlet known for its global news coverage and often controversial, Kremlin-aligned perspectives on major events.
-
D.
RT
RT is the regional vehicle registration code assigned to the city of Tarnobrzeg in Poland.
-
E.
RL
RL is an American R&B singer best known as a member of the group Next and for his smooth vocal contributions to late-1990s and early-2000s R&B hits.
- 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_69ca842f7e3481908bf5bcf52e032dbd |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd51528b2481908ca1f1840d2594b4 |
completed | April 1, 2026, 5:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1011aef64819085cbb7e04c2d87b2 |
completed | April 4, 2026, 12:16 p.m. |
Created at: March 30, 2026, 7:46 p.m.