Triple
T6910493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somewhere in Time |
E159918
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Bid Time Return |
E197016
|
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: Bid Time Return | Statement: [Somewhere in Time, basedOn, Bid Time Return]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bid Time Return Context triple: [Somewhere in Time, basedOn, Bid Time Return]
-
A.
Bid Time Return
chosen
Bid Time Return is a 1975 time-travel romance novel by Richard Matheson that inspired the film "Somewhere in Time."
-
B.
BSE On-Line Trading
BSE On-Line Trading is the electronic trading platform of the Bombay Stock Exchange that enables automated, screen-based securities trading.
-
C.
Premia
Premia is a small municipality in the Verbano-Cusio-Ossola province of Italy, located in the Piedmont region near the Alps.
-
D.
Tesla Autobidder
Tesla Autobidder is Tesla’s real-time trading and control software platform that autonomously optimizes the dispatch and market participation of energy storage assets like Megapacks.
-
E.
Boursorama
Boursorama is a French online bank and financial services company known for its low-cost digital banking and brokerage offerings.
- 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_69c68839ccb88190b4aa5cc1aca3448f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d9c00e948190b103a2b2a2738bb1 |
completed | March 27, 2026, 7:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c749076f6c819088b0b40dd3e208b0 |
completed | March 28, 2026, 3:20 a.m. |
Created at: March 27, 2026, 2:25 p.m.