Triple
T19878720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris-Saclay cluster |
E477707
|
entity |
| Predicate | includesCompany |
P82128
|
FINISHED |
| Object |
Air Liquide
Air Liquide is a leading French multinational company specializing in industrial gases and related technologies for industries and healthcare worldwide.
|
E1399334
|
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: Air Liquide | Statement: [Paris-Saclay cluster, includesCompany, Air Liquide]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Air Liquide Context triple: [Paris-Saclay cluster, includesCompany, Air Liquide]
-
A.
Linde Air Products Company
Linde Air Products Company is an industrial gas and chemical company historically involved in large-scale production and processing operations, including work related to uranium facilities.
-
B.
Linde
Linde is a given name, often used in Germanic and Scandinavian countries, that is related to or derived from the name Linda.
-
C.
Linde
Linde was the reign era name used by Emperor Gaozong during part of his rule over China’s Tang dynasty.
-
D.
Linde
Linde is a village in the Dutch municipality of De Wolden in the province of Drenthe.
-
E.
Technogas
Technogas was a Yugoslav industrial and trading company where future Serbian and Yugoslav president Slobodan Milošević held an early management position.
- 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: Air Liquide Triple: [Paris-Saclay cluster, includesCompany, Air Liquide]
Generated description
Air Liquide is a leading French multinational company specializing in industrial gases and related technologies for industries and healthcare worldwide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Air Liquide Target entity description: Air Liquide is a leading French multinational company specializing in industrial gases and related technologies for industries and healthcare worldwide.
-
A.
Linde Air Products Company
Linde Air Products Company is an industrial gas and chemical company historically involved in large-scale production and processing operations, including work related to uranium facilities.
-
B.
Linde
Linde is a given name, often used in Germanic and Scandinavian countries, that is related to or derived from the name Linda.
-
C.
Linde
Linde was the reign era name used by Emperor Gaozong during part of his rule over China’s Tang dynasty.
-
D.
Linde
Linde is a village in the Dutch municipality of De Wolden in the province of Drenthe.
-
E.
Technogas
Technogas was a Yugoslav industrial and trading company where future Serbian and Yugoslav president Slobodan Milošević held an early management position.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658dd869c81908aed91ee767f5f3d |
completed | April 20, 2026, 4:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07dbca90b08190a2f1d7434ce10758 |
completed | May 16, 2026, 2:51 a.m. |
| NEDg | Description generation | batch_6a07dc950cd8819084a9184a20a15b85 |
completed | May 16, 2026, 2:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07dd016aa88190890d6272e51c30e2 |
completed | May 16, 2026, 2:57 a.m. |
Created at: April 10, 2026, 1:52 p.m.