Triple
T29618115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Airy (Martian crater) |
E754917
|
entity |
| Predicate | hasInnerCrater |
P192004
|
FINISHED |
| Object |
Airy-0 (Martian crater)
Airy-0 is a small crater within the larger Martian crater Airy that historically defined the location of Mars’s prime meridian.
|
E1882402
|
NE FINISHED |
How this triple was built (3 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: Airy-0 (Martian crater) | Statement: [Airy (Martian crater), hasInnerCrater, Airy-0 (Martian crater)]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Airy-0 (Martian crater) Triple: [Airy (Martian crater), hasInnerCrater, Airy-0 (Martian crater)]
Generated description
Airy-0 is a small crater within the larger Martian crater Airy that historically defined the location of Mars’s prime meridian.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInnerCrater Context triple: [Airy (Martian crater), hasInnerCrater, Airy-0 (Martian crater)]
-
A.
hasCrater
Indicates that one entity possesses or features a crater on its surface.
-
B.
hasCraterInterior
chosen
Indicates that one entity is located within the interior region of a crater associated with another entity.
-
C.
hasMultipleCraters
Indicates that an entity possesses or is characterized by more than one crater.
-
D.
hasSatelliteCrater
Indicates that one crater is a secondary or subsidiary crater associated with, and typically located near, another primary crater.
-
E.
hasOverlappingCrater
Indicates that one crater partially or fully overlaps another crater in space, sharing a common area of their surfaces.
- F. None of above.
Provenance (6 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_69f0ef86b6ec8190a87fff07fd983b1e |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69fe9dfaa2d08190b2084f63f842eb6b |
completed | May 9, 2026, 2:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a26aa613a14819090501139c0c4054c |
completed | June 8, 2026, 11:41 a.m. |
| NEDg | Description generation | batch_6a26b557450081909c03ff34c171a007 |
completed | June 8, 2026, 12:28 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a26b934b00c819087c306fb9dbc427d |
completed | June 8, 2026, 12:44 p.m. |
| PD | Predicate disambiguation | batch_69fe9bba947c81908b0b2b92a4d19b37 |
completed | May 9, 2026, 2:28 a.m. |
Created at: April 28, 2026, 6:32 p.m.