Triple
T34587698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Travis McGee series |
E888087
|
entity |
| Predicate | protagonistHouseboatName |
P181290
|
FINISHED |
| Object |
The Busted Flush
The Busted Flush is the dilapidated yet iconic houseboat home and base of operations of fictional salvage consultant Travis McGee in John D. MacDonald’s mystery novels.
|
E1115817
|
NE FINISHED |
How this triple was built (3 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: The Busted Flush | Statement: [Travis McGee series, protagonistHouseboatName, The Busted Flush]
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: The Busted Flush Triple: [Travis McGee series, protagonistHouseboatName, The Busted Flush]
Generated description
The Busted Flush is the dilapidated yet iconic houseboat home and base of operations of fictional salvage consultant Travis McGee in John D. MacDonald’s mystery novels.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protagonistHouseboatName Context triple: [Travis McGee series, protagonistHouseboatName, The Busted Flush]
-
A.
boatTraveledOn
Indicates that a boat moved or was transported along or across a specified body of water or route.
-
B.
seventhBoat
Indicates that an entity is identified specifically as the seventh boat in an ordered sequence or group of boats.
-
C.
hasBoat
Indicates that one entity possesses, owns, or has control over a boat.
-
D.
sixthBoat
Indicates that an entity is the sixth boat in an ordered sequence or arrangement of boats.
-
E.
thirdBoat
Indicates that one entity is the third boat in an ordered sequence or group of boats.
- F. None of above. chosen
Provenance (7 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_69f349d25cbc8190869998de5915886b |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7675b12848190a3569cfda29c5b0e |
completed | May 3, 2026, 3:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a37363f21a48190a7d371f4a50d27f7 |
completed | June 21, 2026, 12:54 a.m. |
| NEDg | Description generation | batch_6a37373c8d2c8190b29f4a91836b6e40 |
completed | June 21, 2026, 12:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a3737bde2e8819099605cf04b5de6f1 |
completed | June 21, 2026, 1 a.m. |
| PD | Predicate disambiguation | batch_69f762f4b59481909f70074f11825bfb |
completed | May 3, 2026, 3 p.m. |
| PDg | Predicate description generation | batch_69f76759b3c48190ad8f1b33596f98c4 |
completed | May 3, 2026, 3:18 p.m. |
Created at: May 1, 2026, 2:03 a.m.