Triple
T8894964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Combines |
E211783
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Rebus |
E733527
|
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: Rebus | Statement: [Combines, notableWork, Rebus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rebus Context triple: [Combines, notableWork, Rebus]
-
A.
Rebus
chosen
Rebus is a British television crime drama series based on Ian Rankin’s Inspector Rebus novels, featuring John Hannah in the title role in its early adaptations.
-
B.
Calligrams
Calligrams is a specialized imprint of New York Review Books focused on publishing distinctive literary and intellectual works, often in translation.
-
C.
Calligrammes
Calligrammes is a celebrated collection of visual and typographic poetry by Guillaume Apollinaire that helped pioneer modernist and avant-garde poetic forms in the early 20th century.
-
D.
Scramble Board
Scramble Board was a popular recurring word-guessing game segment on the television music and dance show "Soul Train."
-
E.
Pennycross
Pennycross is a historic estate in Scotland that served as a principal seat of Clan Maclean.
- 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_69ca83918d3081909b326fa3750cb8c8 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61be2c2081908f39cccdc149872d |
completed | April 1, 2026, 12:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfac02974881908a7e8d9cfa47e624 |
completed | April 3, 2026, 12:01 p.m. |
Created at: March 30, 2026, 6:54 p.m.