Triple
T16920998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ExoMars Trace Gas Orbiter |
E410442
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object |
TGO
TGO is a European-Russian Mars orbiter designed to study trace gases in the Martian atmosphere, particularly methane, to investigate potential geological or biological activity.
|
E1241816
|
NE FINISHED |
How this triple was built (4 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: TGO | Statement: [ExoMars Trace Gas Orbiter, abbreviation, TGO]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TGO Context triple: [ExoMars Trace Gas Orbiter, abbreviation, TGO]
-
A.
TGO
TGO is the three-letter ISO 3166-1 alpha-3 country code assigned to the West African nation of Togo.
-
B.
TOG
TOG is the commonly used abbreviation for The Open Group, an international consortium that develops open, vendor-neutral technology standards and certifications.
-
C.
JGTO
JGTO is the organizing body responsible for running and overseeing the professional men's golf tour in Japan.
-
D.
Can Togay
Can Togay is a Hungarian film director, screenwriter, actor, and cultural figure best known internationally for co-creating the "Shoes on the Danube Bank" Holocaust memorial in Budapest.
-
E.
TUG
TUG (TeX Users Group) is an international organization that supports and promotes the TeX typesetting system and related software.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: TGO Triple: [ExoMars Trace Gas Orbiter, abbreviation, TGO]
Generated description
TGO is a European-Russian Mars orbiter designed to study trace gases in the Martian atmosphere, particularly methane, to investigate potential geological or biological activity.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: TGO Target entity description: TGO is a European-Russian Mars orbiter designed to study trace gases in the Martian atmosphere, particularly methane, to investigate potential geological or biological activity.
-
A.
TGO
TGO is the three-letter ISO 3166-1 alpha-3 country code assigned to the West African nation of Togo.
-
B.
TOG
TOG is the commonly used abbreviation for The Open Group, an international consortium that develops open, vendor-neutral technology standards and certifications.
-
C.
JGTO
JGTO is the organizing body responsible for running and overseeing the professional men's golf tour in Japan.
-
D.
Can Togay
Can Togay is a Hungarian film director, screenwriter, actor, and cultural figure best known internationally for co-creating the "Shoes on the Danube Bank" Holocaust memorial in Budapest.
-
E.
TUG
TUG (TeX Users Group) is an international organization that supports and promotes the TeX typesetting system and related software.
- F. None of above. chosen
Provenance (5 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_69d886c7b1e481908c3766dfa8c13458 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cdee252c81908621b2ca897416e9 |
completed | April 18, 2026, 6:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00cfd3c488819089e3791c7e704baf |
completed | May 10, 2026, 6:34 p.m. |
| NEDg | Description generation | batch_6a00d0e1650881909eacc90cf99787f4 |
completed | May 10, 2026, 6:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00d1e024e88190bfcb50b42f37949b |
completed | May 10, 2026, 6:43 p.m. |
Created at: April 10, 2026, 5:30 a.m.