Triple
T17121618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Williams International |
E415479
|
entity |
| Predicate | hasEngineFamily |
P18926
|
FINISHED |
| Object |
F107
The F107 is a small turbofan engine developed by Williams International, best known for powering various cruise missiles and unmanned aerial vehicles.
|
E1250657
|
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: F107 | Statement: [Williams International, hasEngineFamily, F107]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: F107 Context triple: [Williams International, hasEngineFamily, F107]
-
A.
F100
F100 is the ICAO aircraft type designator for the Fokker 100, a medium-sized twin-turbofan regional jet airliner.
-
B.
H10
H10 is the shorthand name for Hilbert’s tenth problem, a famous decision problem in number theory concerning the solvability of Diophantine equations.
-
C.
F70
F70 is the ICAO type designator for the Fokker 70, a twin-engine regional jet airliner developed by the Dutch manufacturer Fokker.
-
D.
FH10
FH10 is a proprietary vector graphics file format associated with Macromedia FreeHand version 10, used for storing illustrations and page layouts.
-
E.
J100
J100 is the internal model code used by Lexus to designate the second generation of its full-size luxury SUV, the Lexus LX.
- 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: F107 Triple: [Williams International, hasEngineFamily, F107]
Generated description
The F107 is a small turbofan engine developed by Williams International, best known for powering various cruise missiles and unmanned aerial vehicles.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: F107 Target entity description: The F107 is a small turbofan engine developed by Williams International, best known for powering various cruise missiles and unmanned aerial vehicles.
-
A.
F100
F100 is the ICAO aircraft type designator for the Fokker 100, a medium-sized twin-turbofan regional jet airliner.
-
B.
H10
H10 is the shorthand name for Hilbert’s tenth problem, a famous decision problem in number theory concerning the solvability of Diophantine equations.
-
C.
F70
F70 is the ICAO type designator for the Fokker 70, a twin-engine regional jet airliner developed by the Dutch manufacturer Fokker.
-
D.
FH10
FH10 is a proprietary vector graphics file format associated with Macromedia FreeHand version 10, used for storing illustrations and page layouts.
-
E.
J100
J100 is the internal model code used by Lexus to designate the second generation of its full-size luxury SUV, the Lexus LX.
- 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_69d886d090cc8190a39cb94992586905 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3e809ee888190a2cf69d59c0b9c20 |
completed | April 18, 2026, 8:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a013a1062fc8190b1c4e97f42cf3faa |
completed | May 11, 2026, 2:08 a.m. |
| NEDg | Description generation | batch_6a013ae388548190b09d2c81e1ab0d02 |
completed | May 11, 2026, 2:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a013b4df74c81908b3b99e276531e13 |
completed | May 11, 2026, 2:13 a.m. |
Created at: April 10, 2026, 5:36 a.m.