Triple
T14643251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harbaugh Bowl |
E343779
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object |
Harbowl
Harbowl is the popular nickname for the Super Bowl XLVII matchup between the Baltimore Ravens and San Francisco 49ers, coached by brothers John and Jim Harbaugh.
|
E1112592
|
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: Harbowl | Statement: [Harbaugh Bowl, hasAlternativeName, Harbowl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harbowl Context triple: [Harbaugh Bowl, hasAlternativeName, Harbowl]
-
A.
Harbo
Harbo is a small locality in central Sweden situated within Heby Municipality in Uppsala County.
-
B.
Hawzen
Hawzen is a town in northern Ethiopia’s Tigray Region, known for its nearby rock-hewn churches and its role in the region’s modern conflicts.
-
C.
Harborland
Harborland is a popular waterfront shopping and entertainment district in Kobe, Japan, known for its modern malls, restaurants, and scenic harbor views.
-
D.
Hakeburg
Hakeburg is a historic castle-like manor and former research facility located in Kleinmachnow, Germany.
-
E.
Saltpond
Saltpond is a coastal town in Ghana known historically as a trading center and for its role in the country’s early political and educational development.
- 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: Harbowl Triple: [Harbaugh Bowl, hasAlternativeName, Harbowl]
Generated description
Harbowl is the popular nickname for the Super Bowl XLVII matchup between the Baltimore Ravens and San Francisco 49ers, coached by brothers John and Jim Harbaugh.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Harbowl Target entity description: Harbowl is the popular nickname for the Super Bowl XLVII matchup between the Baltimore Ravens and San Francisco 49ers, coached by brothers John and Jim Harbaugh.
-
A.
Harbo
Harbo is a small locality in central Sweden situated within Heby Municipality in Uppsala County.
-
B.
Hawzen
Hawzen is a town in northern Ethiopia’s Tigray Region, known for its nearby rock-hewn churches and its role in the region’s modern conflicts.
-
C.
Harborland
Harborland is a popular waterfront shopping and entertainment district in Kobe, Japan, known for its modern malls, restaurants, and scenic harbor views.
-
D.
Hakeburg
Hakeburg is a historic castle-like manor and former research facility located in Kleinmachnow, Germany.
-
E.
Saltpond
Saltpond is a coastal town in Ghana known historically as a trading center and for its role in the country’s early political and educational development.
- F. None of above. chosen
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_69d822e1a2cc81908e5bb93cf61ce3cc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4e80aa48190884bab800f357106 |
completed | April 14, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdd5d404e881908d26e684702ae122 |
completed | May 8, 2026, 12:23 p.m. |
| NEDg | Description generation | batch_69fdd9dbdf448190ad40ba07f586b4f6 |
completed | May 8, 2026, 12:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fdda3a7ea08190bc65641681da00cc |
completed | May 8, 2026, 12:42 p.m. |
Created at: April 10, 2026, 1:26 a.m.