Triple
T13538139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arkema |
E323313
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object |
ArrMaz
ArrMaz is a specialty chemicals company known for producing additives and process aids for industries such as fertilizers, mining, asphalt, and industrial minerals.
|
E1047917
|
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: ArrMaz | Statement: [Arkema, hasSubsidiary, ArrMaz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ArrMaz Context triple: [Arkema, hasSubsidiary, ArrMaz]
-
A.
MAZ
MAZ is the IATA airport code for Eugenio María de Hostos Airport, a regional airport serving Mayagüez in western Puerto Rico.
-
B.
Tajazai
Tajazai is a village and settlement located in the Lakki Marwat District of Khyber Pakhtunkhwa province in Pakistan.
-
C.
GMAZ
GMAZ is the ICAO airport code for Zagora Airport in Morocco.
-
D.
Mazz
Mazz is a pioneering and influential Tejano band known for modernizing the genre with a distinctive blend of traditional Mexican music and contemporary pop sounds.
-
E.
Alimos
Alimos is a coastal suburb in the southern part of Athens, Greece, known for its marina and beaches along the Saronic Gulf.
- 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: ArrMaz Triple: [Arkema, hasSubsidiary, ArrMaz]
Generated description
ArrMaz is a specialty chemicals company known for producing additives and process aids for industries such as fertilizers, mining, asphalt, and industrial minerals.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: ArrMaz Target entity description: ArrMaz is a specialty chemicals company known for producing additives and process aids for industries such as fertilizers, mining, asphalt, and industrial minerals.
-
A.
MAZ
MAZ is the IATA airport code for Eugenio María de Hostos Airport, a regional airport serving Mayagüez in western Puerto Rico.
-
B.
Tajazai
Tajazai is a village and settlement located in the Lakki Marwat District of Khyber Pakhtunkhwa province in Pakistan.
-
C.
GMAZ
GMAZ is the ICAO airport code for Zagora Airport in Morocco.
-
D.
Mazz
Mazz is a pioneering and influential Tejano band known for modernizing the genre with a distinctive blend of traditional Mexican music and contemporary pop sounds.
-
E.
Alimos
Alimos is a coastal suburb in the southern part of Athens, Greece, known for its marina and beaches along the Saronic Gulf.
- 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_69d8076776248190bdf0d4fa1f85a5fc |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbafbe39948190808062d4eff91841 |
completed | April 12, 2026, 2:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f75d9c04b881908a359df791b89b43 |
completed | May 3, 2026, 2:37 p.m. |
| NEDg | Description generation | batch_69f761e020708190a21ad4c0bc11d730 |
completed | May 3, 2026, 2:55 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f765d0f9d88190b91097a359043860 |
completed | May 3, 2026, 3:12 p.m. |
Created at: April 9, 2026, 9:45 p.m.