Triple
T6006250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kering |
E133716
|
entity |
| Predicate | brandPortfolio |
P12124
|
FINISHED |
| Object | Pomellato |
E553726
|
NE FINISHED |
How this triple was built (2 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: Pomellato | Statement: [Kering, brandPortfolio, Pomellato]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pomellato Context triple: [Kering, brandPortfolio, Pomellato]
-
A.
Pomellato
chosen
Pomellato is an Italian luxury jewelry brand renowned for its colorful gemstone designs and contemporary, handcrafted pieces.
-
B.
Chaumet
Chaumet is a historic French high jewelry and watchmaking house renowned for its exquisite tiaras and fine craftsmanship.
-
C.
Boucheron
Boucheron is a historic French luxury jewelry and watchmaking house renowned for its high-end, artistic designs and craftsmanship.
-
D.
Cartier
Cartier is a renowned French luxury jewelry and watchmaker celebrated worldwide for its high-end timepieces, fine jewelry, and iconic designs.
-
E.
Van Cleef & Arpels
Van Cleef & Arpels is a renowned French luxury jewelry, watch, and perfume house celebrated for its high-end craftsmanship and iconic, poetic designs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c00872444c8190bfaf1739dcec765c |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f128354819088971ee398cbda77 |
completed | March 22, 2026, 8:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c1250c82588190af8102263c1bd242 |
completed | March 23, 2026, 11:33 a.m. |
Created at: March 22, 2026, 4:06 p.m.