Triple
T8418407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lady Speed Stick |
E198785
|
entity |
| Predicate | partOfBrandFamily |
P11218
|
FINISHED |
| Object | Speed Stick |
E38986
|
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: Speed Stick | Statement: [Lady Speed Stick, partOfBrandFamily, Speed Stick]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Speed Stick Context triple: [Lady Speed Stick, partOfBrandFamily, Speed Stick]
-
A.
Speed Stick
chosen
Speed Stick is a popular line of men’s deodorant and antiperspirant products known for its solid stick format and long-lasting odor protection.
-
B.
Lady Speed Stick
Lady Speed Stick is a women-focused line of antiperspirant and deodorant products marketed under the Speed Stick brand.
-
C.
The Stick
The Stick is the longtime nickname of Candlestick Park, the former outdoor sports stadium in San Francisco that famously hosted the San Francisco Giants and 49ers.
-
D.
Stikker
Stikker is a surname most notably associated with Dirk Stikker, a Dutch politician and diplomat who served as NATO Secretary General.
-
E.
Fastest Skater
Fastest Skater is an NHL All-Star skills competition event that showcases which player can complete a lap around the rink in the shortest time.
- 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_69ca8312d63c8190bf133b676b44a385 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb84c7d6e48190a2bbde89c5d42af6 |
completed | March 31, 2026, 8:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce3988932c8190969c4c0295348636 |
completed | April 2, 2026, 9:40 a.m. |
Created at: March 30, 2026, 6:06 p.m.