Triple
T14116291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Procter & Gamble Company |
E339784
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | Tide |
E339785
|
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: Tide | Statement: [Procter & Gamble Company, brand, Tide]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tide Context triple: [Procter & Gamble Company, brand, Tide]
-
A.
Tide
chosen
Tide is a leading American laundry detergent brand known for its powerful stain-removal formulas and wide range of fabric care products.
-
B.
The Tide
The Tide is a light rail transit system serving the city of Norfolk in southeastern Virginia.
-
C.
The Tide
The Tide is a common shorthand for the University of Alabama’s storied Crimson Tide athletic programs, especially its powerhouse college football team.
-
D.
TIDE
TIDE is a U.S. government centralized database that stores and manages information on known or suspected terrorists for use by intelligence and security agencies.
-
E.
Wash
"Wash" is a popular electronic dance music track by Nigerian producer and DJ Tekno, known for its catchy melody and club-friendly beat.
- 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_69d81c6a95b481909e39111e0c1f31ee |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de6010a03c81909f5f160f8d1fa8fa |
completed | April 14, 2026, 3:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0baa328819099511dfa7b9666d3 |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:22 p.m.