Triple

T22717548
Position Surface form Disambiguated ID Type / Status
Subject Elf Aquitaine E561774 entity
Predicate parentCompanyOf P254 FINISHED
Object Elf Antar France
Elf Antar France was a French petroleum and lubricants company that operated as a subsidiary of the major oil group Elf Aquitaine.
E1550572 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: Elf Antar France | Statement: [Elf Aquitaine, parentCompanyOf, Elf Antar France]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elf Antar France
Context triple: [Elf Aquitaine, parentCompanyOf, Elf Antar France]
  • A. Altran
    Altran is a global engineering and R&D services company, now operating as part of Capgemini Engineering after its acquisition by Capgemini.
  • B. Lafare
    Lafare is a small commune in southeastern France’s Vaucluse department, known for its picturesque vineyards and location within the Côtes du Rhône wine region.
  • C. Arvier
    Arvier is a small mountain commune in Italy’s Aosta Valley, known for its alpine scenery and traditional wine production.
  • D. Delarue
    Delarue is a vengeful ex-soldier and gunslinger who serves as the main protagonist in the Western thriller film "The Salvation."
  • E. Gsell
    Gsell is a surname of Germanic origin borne by various notable individuals, including artists, scholars, and public figures.
  • 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: Elf Antar France
Triple: [Elf Aquitaine, parentCompanyOf, Elf Antar France]
Generated description
Elf Antar France was a French petroleum and lubricants company that operated as a subsidiary of the major oil group Elf Aquitaine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Elf Antar France
Target entity description: Elf Antar France was a French petroleum and lubricants company that operated as a subsidiary of the major oil group Elf Aquitaine.
  • A. Altran
    Altran is a global engineering and R&D services company, now operating as part of Capgemini Engineering after its acquisition by Capgemini.
  • B. Lafare
    Lafare is a small commune in southeastern France’s Vaucluse department, known for its picturesque vineyards and location within the Côtes du Rhône wine region.
  • C. Arvier
    Arvier is a small mountain commune in Italy’s Aosta Valley, known for its alpine scenery and traditional wine production.
  • D. Delarue
    Delarue is a vengeful ex-soldier and gunslinger who serves as the main protagonist in the Western thriller film "The Salvation."
  • E. Gsell
    Gsell is a surname of Germanic origin borne by various notable individuals, including artists, scholars, and public figures.
  • 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_69e2454fc984819088213b58ee87a002 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1790ecbc48190926d16b20b674dbd completed April 29, 2026, 3:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b7edf9c988190ba19b094f3232c87 completed May 18, 2026, 9:04 p.m.
NEDg Description generation batch_6a0b8076dd848190b7ee7c745ddee3c5 completed May 18, 2026, 9:11 p.m.
NED2 Entity disambiguation (via description) batch_6a0b819ebe90819088593ffcd70251b1 completed May 18, 2026, 9:16 p.m.
Created at: April 17, 2026, 3:19 p.m.