Triple
T11537400
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phoenix Pride parade |
E273584
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Phoenix |
E9582
|
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: Phoenix | Statement: [Phoenix Pride parade, city, Phoenix]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Phoenix Context triple: [Phoenix Pride parade, city, Phoenix]
-
A.
Phoenix
chosen
Phoenix is the capital and largest city of the U.S. state of Arizona, known for its desert climate, rapid growth, and role as a major economic and cultural center in the American Southwest.
-
B.
Phoenix
Phoenix is the mythical bird that cyclically regenerates from its own ashes, symbolizing rebirth and renewal.
-
C.
Phoenix
Phoenix is a British publishing imprint known for releasing a wide range of fiction and non-fiction titles under the Orion Publishing Group.
-
D.
Phoenix
Phoenix is a social and dining club at Harvard University known for its exclusive membership and long-standing traditions.
-
E.
Phoenix
Phoenix is a high-performance web development framework for the Elixir programming language, designed for building scalable, real-time applications.
- 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_69d6aae3fbec8190a14632a5df2538b6 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8839cdf688190ae75c0e6fece8e33 |
completed | April 10, 2026, 4:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e684d1bcd08190925cc9a2e844c900 |
completed | April 20, 2026, 7:56 p.m. |
Created at: April 8, 2026, 9:37 p.m.