Triple
T14487224
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LXS |
E359262
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object |
LGLM
LGLM is the ICAO airport code for Limnos International Airport, serving the island of Lemnos in Greece.
|
E1100550
|
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: LGLM | Statement: [LXS, ICAOcode, LGLM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LGLM Context triple: [LXS, ICAOcode, LGLM]
-
A.
GLM
GLM is the National Rail station code for Gillingham railway station in Kent, England.
-
B.
GLR
GLR is the IATA airport code for Gaylord Regional Airport, a public airport serving the Gaylord area in Michigan, United States.
-
C.
Bayesian logistic regression
Bayesian logistic regression is a probabilistic classification method that models binary outcomes using a logistic link function with prior distributions on the parameters, enabling full Bayesian inference and uncertainty quantification.
-
D.
LogisticRegression
LogisticRegression is a scikit-learn machine learning estimator that models the probability of class membership using a linear decision boundary with logistic (sigmoid) or related link functions.
-
E.
LR-GG
LR-GG is the ISO 3166-2 subdivision code assigned to Grand Gedeh County in Liberia.
- 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: LGLM Triple: [LXS, ICAOcode, LGLM]
Generated description
LGLM is the ICAO airport code for Limnos International Airport, serving the island of Lemnos in Greece.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: LGLM Target entity description: LGLM is the ICAO airport code for Limnos International Airport, serving the island of Lemnos in Greece.
-
A.
GLM
GLM is the National Rail station code for Gillingham railway station in Kent, England.
-
B.
GLR
GLR is the IATA airport code for Gaylord Regional Airport, a public airport serving the Gaylord area in Michigan, United States.
-
C.
Bayesian logistic regression
Bayesian logistic regression is a probabilistic classification method that models binary outcomes using a logistic link function with prior distributions on the parameters, enabling full Bayesian inference and uncertainty quantification.
-
D.
LogisticRegression
LogisticRegression is a scikit-learn machine learning estimator that models the probability of class membership using a linear decision boundary with logistic (sigmoid) or related link functions.
-
E.
LR-GG
LR-GG is the ISO 3166-2 subdivision code assigned to Grand Gedeh County in Liberia.
- 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_69d8279740308190af9df93a3af8592e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de924ee0f08190baf68318b41fa64d |
completed | April 14, 2026, 7:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd64a925148190992101984895a20b |
completed | May 8, 2026, 4:20 a.m. |
| NEDg | Description generation | batch_69fd65ae2ef0819091c7576b9cfe5fe2 |
completed | May 8, 2026, 4:25 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd66476ab88190b2d410ced33ce34b |
completed | May 8, 2026, 4:27 a.m. |
Created at: April 10, 2026, 1:20 a.m.