Triple
T22924456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marooned on Mars |
E569261
|
entity |
| Predicate | setting |
P1957
|
FINISHED |
| Object | Mars |
—
|
NE NERFINISHED |
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: Mars | Statement: [Marooned on Mars, setting, Mars]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mars Context triple: [Marooned on Mars, setting, Mars]
-
A.
Mars
chosen
Mars is the fourth planet from the Sun, a cold, desert-like world often called the "Red Planet" due to its iron-rich surface and a prime target in the search for past or present extraterrestrial life.
-
B.
Mars
Mars is the Roman god of war, a central deity in Roman religion associated with military power, agriculture, and the fatherhood of Rome’s legendary founders.
-
C.
Mars
Mars is a science fiction television series produced by Imagine Television that blends scripted drama with documentary-style elements to depict humanity’s efforts to colonize the Red Planet.
-
D.
Mars
Mars is an American hip hop record producer known for his work on various rap projects, including contributions to major studio albums.
-
E.
Mars
Mars is a major global manufacturer of confectionery, pet care products, and other food items, known for brands like M&M’s, Snickers, and Pedigree.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2458f7d008190901dccbaebeaba24 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f180d84fc08190b747c3f9052c657a |
completed | April 29, 2026, 3:54 a.m. |
Created at: April 17, 2026, 3:43 p.m.