Triple
T12378237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Washington Spirit |
E295678
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object |
Spirit
Spirit is the nickname of the Washington Spirit, a professional women's soccer team competing in the National Women's Soccer League (NWSL).
|
E295678
|
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: Spirit | Statement: [Washington Spirit, nickname, Spirit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Spirit Context triple: [Washington Spirit, nickname, Spirit]
-
A.
Spirit
Spirit was one of NASA's twin Mars Exploration Rovers, a robotic rover that explored the Martian surface to study its geology and past environmental conditions.
-
B.
Spirit
Spirit is a stage production that blends dance, drumming, and vocal performance to celebrate Indigenous culture and storytelling.
-
C.
Spirit
Spirit is a lyricist known for writing the words to the song "Too Sick to Pray."
-
D.
Spirit
Spirit is a song composed by the artist Matador.
-
E.
Spirit
Spirit is the second studio album by English singer Leona Lewis, featuring the global hit single "Bleeding Love" and known for its powerful pop and R&B ballads.
- 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: Spirit Triple: [Washington Spirit, nickname, Spirit]
Generated description
Spirit is the nickname of the Washington Spirit, a professional women's soccer team competing in the National Women's Soccer League (NWSL).
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Spirit Target entity description: Spirit is the nickname of the Washington Spirit, a professional women's soccer team competing in the National Women's Soccer League (NWSL).
-
A.
Spirit
chosen
Spirit is a professional women’s soccer team competing in the National Women’s Soccer League and based in the Washington, D.C. area.
-
B.
Spirit
Spirit is the NATO reporting name for the Northrop Grumman B-2, a long-range stealth strategic bomber used by the United States Air Force.
-
C.
Spirit
Spirit was one of NASA's twin Mars Exploration Rovers, a robotic rover that explored the Martian surface to study its geology and past environmental conditions.
-
D.
Spirit
Spirit is the second studio album by English singer Leona Lewis, featuring the global hit single "Bleeding Love" and known for its powerful pop and R&B ballads.
-
E.
Spirit
Spirit is an American rock band formed in the late 1960s, known for its eclectic blend of psychedelic rock, jazz, and progressive influences.
- F. None of above.
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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fb8d6c081909e8bbbd52c73f29c |
completed | April 10, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f634760210819080bc0261aa059132 |
completed | May 2, 2026, 5:29 p.m. |
| NEDg | Description generation | batch_69f6356b545c819089a5f5b901afc5f2 |
completed | May 2, 2026, 5:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f636382ffc8190becfae41757a45d8 |
completed | May 2, 2026, 5:36 p.m. |
Created at: April 8, 2026, 9:54 p.m.